© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106977
    Prev
    Next
    INDEX
    Explanations

    docker container commands

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

    This neuron picks out numeric tokens (raw counts, IDs, sizes, etc.) in CLI output.

    oai_token-act-pair · o4-miniTriggered 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
     parç
    -0.76
     Conceptual
    -0.76
    offsetWidth
    -0.73
    Conceptual
    -0.72
     jumbo
    -0.72
    ք
    -0.72
    Tien
    -0.71
     edema
    -0.71
     MacBook
    -0.69
    ఱ
    -0.69
    POSITIVE LOGITS
     container
    1.34
     containers
    1.20
     Container
    1.13
     контей
    1.11
    container
    1.11
    sandbox
    1.11
    Container
    1.07
    containers
    1.05
     sandbox
    0.97
    Containers
    0.96
    Activations Density 0.062%

    No Known Activations