© 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. 127934
    Prev
    Next
    INDEX
    Explanations

    common programming identifiers

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

    The neuron fires on programming type or class names (e.g. Buffer, List, PositionInMenu, android).

    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
     has
    -1.95
     first
    -1.87
     other
    -1.67
     are
    -1.63
     utilizamos
    -1.50
     does
    -1.49
    黩
    -1.48
     vendido
    -1.47
     got
    -1.46
     conseguido
    -1.46
    POSITIVE LOGITS
    :
    2.31
     gants
    1.70
    erobic
    1.64
     verres
    1.54
    ܇
    1.51
     suffisamment
    1.48
     adage
    1.45
    tismo
    1.44
     alre
    1.44
    (“
    1.43
    Activations Density 0.030%

    No Known Activations