Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109953
    Prev
    Next
    INDEX
    Explanations

    statistical tests

    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
    控
    -0.85
     kvad
    -0.77
     działal
    -0.75
     inference
    -0.75
    inference
    -0.74
     گو
    -0.74
    valet
    -0.74
    ཻ
    -0.70
     penumpang
    -0.68
     Todas
    -0.68
    POSITIVE LOGITS
     goodness
    1.05
     Kol
    1.00
     Goodness
    0.98
     KS
    0.92
    Goodness
    0.88
    kst
    0.83
    Kol
    0.82
    KS
    0.81
     Shapiro
    0.80
     ks
    0.77
    Activations Density 0.015%

    No Known Activations