© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79230
    Prev
    Next
    INDEX
    Explanations

    first or default

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

    The neuron fires on identifiers of programming APIs or methods (e.g. capitalized function calls like FirstOrDefault, Where, Select, Any, etc.)

    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
    würdig
    -0.92
    seks
    -0.90
    itates
    -0.90
    SqlParameter
    -0.89
    oltà
    -0.88
    鵜
    -0.87
     enrique
    -0.86
     homenagem
    -0.85
    impro
    -0.84
    ंत्र
    -0.84
    POSITIVE LOGITS
     or
    1.19
    OrDefault
    0.82
    tenti
    0.81
    𝙡
    0.78
    last
    0.77
    匹
    0.76
    OrNull
    0.76
    ⣄
    0.75
     of
    0.74
    insertar
    0.73
    Activations Density 0.007%

    No Known Activations