© 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. 64162
    Prev
    Next
    INDEX
    Explanations

    appointed captain-coach

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

    This neuron specializes in spotting programming/code syntax elements (e.g. keywords, operators, parentheses, and other code‐style 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_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
     Sends
    -0.68
    RTCK
    -0.68
     Shakira
    -0.65
     白色
    -0.65
    ガタ
    -0.64
    onnen
    -0.64
    骏
    -0.63
     Nek
    -0.63
     foreach
    -0.63
     FRI
    -0.63
    POSITIVE LOGITS
     vocación
    0.70
    gint
    0.68
     ilustraciones
    0.68
     Vian
    0.68
     случаи
    0.67
     forecasting
    0.65
    panda
    0.65
    ey
    0.64
     Rah
    0.63
     zakresie
    0.62
    Activations Density 0.080%

    No Known Activations