© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1143
    Prev
    Next
    INDEX
    Explanations

    task completion or success

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron primarily detects numeric tokens (e.g., digits, version numbers, counts) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical documentation describing processes or commands that complete, finish, or succeed.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of program or task completion and outcome status—such as finishing, succeeding/failing, exit/return values, and waiting for threads/operations to be done.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    енный
    -0.74
     coagulation
    -0.73
     折り
    -0.73
    cutta
    -0.72
    INCE
    -0.71
    螨
    -0.70
    UTUP
    -0.70
    atek
    -0.70
     Trot
    -0.70
    FILE
    -0.70
    POSITIVE LOGITS
     completes
    2.64
     completed
    2.19
     completing
    2.16
     completar
    1.82
     completion
    1.82
    completed
    1.79
     finishes
    1.74
     finish
    1.73
     finishing
    1.69
    Comple
    1.66
    Activations Density 0.121%

    No Known Activations