© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64928
    Prev
    Next
    INDEX
    Explanations

    file paths and commit hashes

    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
    ል
    -0.82
     where
    -0.81
     in
    -0.79
     气
    -0.79
     things
    -0.77
    メン
    -0.75
     from
    -0.75
    indra
    -0.75
     after
    -0.73
     Who
    -0.72
    POSITIVE LOGITS
     nessuna
    0.96
     numai
    0.91
    óa
    0.91
     nessun
    0.86
    puts
    0.86
    lysses
    0.85
     Ghe
    0.84
    9
    0.84
     gă
    0.84
     nessuno
    0.84
    Activations Density 0.037%

    No Known Activations