© 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. 35970
    Prev
    Next
    INDEX
    Explanations

    actions taken in studies

    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
     it
    -1.40
     you
    -1.36
     even
    -1.34
     chré
    -1.34
     just
    -1.33
     what
    -1.27
     seems
    -1.27
     religieuses
    -1.19
     how
    -1.16
     berbagai
    -1.15
    POSITIVE LOGITS
    ֶּ
    1.66
     hierdie
    1.48
     scheduled
    1.46
     кроссовки
    1.44
     interview
    1.41
    MatIconModule
    1.35
     was
    1.27
    gelegen
    1.25
    ַּ
    1.25
     agreed
    1.25
    Activations Density 0.209%

    No Known Activations