© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75633
    Prev
    Next
    INDEX
    Explanations

    specific concepts and categories

    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
     chiefly
    -1.25
     whereas
    -1.17
    ologic
    -1.14
     mida
    -1.13
     dreadful
    -1.05
     periodical
    -1.05
     venne
    -1.04
     exceedingly
    -1.03
     reputación
    -1.02
     gebraucht
    -1.02
    POSITIVE LOGITS
     of
    1.67
     in
    1.45
     with
    1.35
     regurg
    1.04
     that
    0.97
     págs
    0.95
     at
    0.94
     نیز
    0.93
     "",
    0.91
     crumbs
    0.91
    Activations Density 0.063%

    No Known Activations