© 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. 118611
    Prev
    Next
    INDEX
    Explanations

    code or specific tokens

    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
    8
    -0.72
    ʕ
    -0.68
     Eighty
    -0.68
    蕙
    -0.66
     ten
    -0.66
     deceiving
    -0.65
     Forty
    -0.65
     affectionate
    -0.64
    clustering
    -0.64
     đu
    -0.63
    POSITIVE LOGITS
     Matthias
    0.82
     yore
    0.73
    ваем
    0.72
     Grenz
    0.71
    Jones
    0.71
     Jurist
    0.70
     pauper
    0.69
    FromArray
    0.68
     Jones
    0.68
     HORSE
    0.68
    Activations Density 0.310%

    No Known Activations