© 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. 64628
    Prev
    Next
    INDEX
    Explanations

    calls, container, getSession, configure, schedule, workspace, execute, batch

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

    The neuron flags tokens characteristic of programming code or API calls—especially punctuation separators (dots, slashes), version numbers, and code identifiers.

    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
     Includes
    -0.84
     Uniwers
    -0.75
    chiff
    -0.73
    telde
    -0.73
     וד
    -0.69
    Includes
    -0.69
     inclui
    -0.68
     INCLUDES
    -0.66
    ņ
    -0.66
     viejas
    -0.66
    POSITIVE LOGITS
    ecraft
    0.85
     provoquer
    0.84
    icae
    0.82
    ishment
    0.81
     歩
    0.79
    gregor
    0.79
     Cleo
    0.79
    wärts
    0.79
    IW
    0.78
    lioz
    0.77
    Activations Density 0.037%

    No Known Activations