© 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. 118992
    Prev
    Next
    INDEX
    Explanations

    W3C documents

    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
    нутри
    -0.92
     Puj
    -0.84
     pneus
    -0.82
     empie
    -0.81
    thée
    -0.80
     
    -0.79
     UW
    -0.77
    ⇔
    -0.77
     statistik
    -0.77
     motorway
    -0.77
    POSITIVE LOGITS
     WC
    0.99
     wc
    0.84
    WC
    0.82
    wc
    0.79
    German
    0.73
    بینی
    0.72
    Fields
    0.71
    ドイツ
    0.71
    ónicas
    0.71
    Phen
    0.70
    Activations Density 0.015%

    No Known Activations