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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98658
    Prev
    Next
    INDEX
    Explanations

    lists items separated by commas or 'and'

    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
     dira
    -1.05
    tifications
    -1.04
    atürk
    -1.02
     Octobre
    -0.98
    continence
    -0.96
     SERVICE
    -0.95
     autorisation
    -0.95
    vocations
    -0.94
     Septembre
    -0.94
    atschapp
    -0.93
    POSITIVE LOGITS
     where
    1.08
     last
    0.89
     Different
    0.85
    多个
    0.83
     notes
    0.82
    ਫ਼
    0.82
     using
    0.80
     which
    0.80
     близько
    0.79
    Different
    0.77
    Activations Density 0.003%

    No Known Activations