© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118838
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Usted
    -0.73
    èce
    -0.68
    Estás
    -0.68
    amemnon
    -0.67
    library
    -0.67
    TIR
    -0.65
    izhou
    -0.65
     cementerio
    -0.64
    اكل
    -0.64
    bunga
    -0.63
    POSITIVE LOGITS
    TG
    0.73
     scala
    0.73
    dispatchEvent
    0.72
    вался
    0.70
    IDENTIFIER
    0.69
    валась
    0.69
     Simons
    0.68
     pasi
    0.68
    𝒶
    0.68
     Г
    0.67
    Activations Density 0.069%

    No Known Activations