© 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. 63044
    Prev
    Next
    INDEX
    Explanations

    programmatically defined attributes

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

    The neuron fires on programming‐style identifiers—names of classes, methods, types, constants, etc.—in source code or config files.

    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
    IKit
    -0.82
    рой
    -0.82
     Intru
    -0.77
    Println
    -0.76
     {$
    -0.75
     soja
    -0.74
    ကို
    -0.74
    レーキ
    -0.74
     такое
    -0.73
    setAccessible
    -0.71
    POSITIVE LOGITS
     num
    1.17
    num
    1.13
     expr
    1.05
    NUM
    0.92
    expr
    0.85
    ňov
    0.81
     étendue
    0.75
    psf
    0.75
     iluminación
    0.74
    arg
    0.72
    Activations Density 0.002%

    No Known Activations