© 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. 10-GEMMASCOPE-RES-131K
    7. 71404
    Prev
    Next
    INDEX
    Explanations

    data parsing or identifiers

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

    The neuron fires on programming‐style identifiers (CamelCase or API/function names) and other technical code tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Of
    -2.80
     When
    -2.77
     With
    -2.70
     distraught
    -2.67
     That
    -2.61
     There
    -2.52
     Seeing
    -2.50
    鋱
    -2.44
     Using
    -2.33
    籥
    -2.33
    POSITIVE LOGITS
    栳
    2.88
    鈇
    2.73
    sandalia
    2.72
    嶮
    2.63
    皤
    2.50
    袮
    2.44
    鼇
    2.36
     importantly
    2.36
    戗
    2.33
    CurtirCurtir
    2.31
    Activations Density 0.001%

    No Known Activations