© 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. 118696
    Prev
    Next
    INDEX
    Explanations

    filed dates

    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
    acty
    -0.74
    скан
    -0.70
     Fuerza
    -0.70
    IMER
    -0.69
    adav
    -0.68
     obč
    -0.68
    Chara
    -0.68
     органі
    -0.68
     liturgy
    -0.67
    本線
    -0.66
    POSITIVE LOGITS
    veaux
    0.85
    Neill
    0.73
    ٥
    0.73
    phospho
    0.73
    encyclo
    0.73
     össze
    0.73
     oito
    0.72
    ductory
    0.71
     截图
    0.69
     Tasse
    0.69
    Activations Density 0.018%

    No Known Activations