© 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. 22-GEMMASCOPE-RES-131K
    4. 68688
    Prev
    Next
    INDEX
    Explanations

    books and publishers

    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_22/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
     if
    -2.22
     as
    -2.20
     this
    -2.19
     in
    -2.17
     any
    -2.16
     one
    -2.09
     while
    -2.09
     before
    -2.06
     epitom
    -2.02
     an
    -2.00
    POSITIVE LOGITS
     Dinas
    2.16
     faciliter
    2.09
     constater
    1.92
     bascul
    1.92
     corriger
    1.91
     materie
    1.87
     interrom
    1.86
     ſol
    1.73
     conster
    1.73
     assister
    1.71
    Activations Density 0.010%

    No Known Activations