© 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. 118660
    Prev
    Next
    INDEX
    Explanations

    times and durations

    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
     divul
    -0.89
    כשיו
    -0.79
    HOURS
    -0.74
     in
    -0.73
    hamos
    -0.67
    czego
    -0.65
    örös
    -0.65
    Դ
    -0.65
     Accesat
    -0.64
     trusts
    -0.63
    POSITIVE LOGITS
     Fifteen
    1.17
    ۳۰
    1.01
     Thirty
    0.93
    ⌧
    0.93
    Fifteen
    0.86
    ອ
    0.84
    atay
    0.82
     thirty
    0.80
     условий
    0.79
     Beaches
    0.78
    Activations Density 0.022%

    No Known Activations