© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2865
    Prev
    Next
    INDEX
    Explanations

    Excel file operations and exports

    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
     techniques
    -0.80
     ฉ
    -0.77
     RHS
    -0.74
    keV
    -0.74
    ìn
    -0.72
    Ale
    -0.70
    kelijkheid
    -0.69
     después
    -0.68
    фор
    -0.68
     delegation
    -0.68
    POSITIVE LOGITS
     olivat
    0.89
     nyingi
    0.84
    pck
    0.82
    パッケージ
    0.79
     rng
    0.79
    rng
    0.79
     tehdä
    0.77
     レモン
    0.77
     eivät
    0.77
     päät
    0.77
    Activations Density 0.012%

    No Known Activations