© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111276
    Prev
    Next
    INDEX
    Explanations

    class/struct/variable names

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

    single uppercase letters used as variable or type names in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on isolated single‐letter uppercase identifiers (e.g. R, U, V, N, S) commonly used as variable or type names.

    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
    媜
    -2.16
     For
    -2.16
     accessoires
    -2.05
     uuidv
    -2.02
    鮠
    -1.98
     bengal
    -1.96
    鰨
    -1.95
    
    -1.92
    𓋼
    -1.91
    titial
    -1.90
    POSITIVE LOGITS
    ANIEL
    2.45
     you
    2.27
     of
    2.03
     quintessential
    2.02
     จะ
    1.97
     tenté
    1.93
    in
    1.91
    再多
    1.88
     religiosos
    1.88
     данного
    1.87
    Activations Density 0.040%

    No Known Activations