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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33581
    Prev
    Next
    INDEX
    Explanations

    Assisted death, Computer systems

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

    This neuron activates on numeric tokens, i.e. literal numbers appearing in the code.

    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
     シングル
    -0.78
    antan
    -0.78
     JOSÉ
    -0.77
    "></
    -0.76
    Today
    -0.75
    addContainerGap
    -0.74
     Vordergrund
    -0.74
    atero
    -0.73
    нулись
    -0.72
    ={{
    -0.72
    POSITIVE LOGITS
     style
    1.08
    style
    0.92
    engan
    0.80
     scold
    0.80
     Himmel
    0.80
    同事
    0.77
     literal
    0.76
     children
    0.76
     эн
    0.76
    presas
    0.75
    Activations Density 0.004%

    No Known Activations