© 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. 22-GEMMASCOPE-RES-131K
    7. 13379
    Prev
    Next
    INDEX
    Explanations

    code structure and operations

    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
     but
    -1.22
    了不少
    -1.20
    https
    -1.20
     essendo
    -1.14
     ও
    -1.14
     &[
    -1.10
     @
    -1.09
     متری
    -1.09
    ">!
    -1.08
    IBOutlet
    -1.06
    POSITIVE LOGITS
     yaka
    1.22
     Nedir
    1.20
     malu
    1.19
     tradis
    1.18
     restoran
    1.16
     ilan
    1.16
    uç
    1.15
     utk
    1.15
     Gün
    1.14
    ѵ
    1.14
    Activations Density 0.015%

    No Known Activations