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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15961
    Prev
    Next
    INDEX
    Explanations

    specific terms and concepts

    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
    śle
    -0.81
    펀
    -0.81
    ȴ
    -0.76
    ȣ
    -0.76
     Categoria
    -0.76
     speziellen
    -0.75
    জি
    -0.75
     никогда
    -0.75
     differenza
    -0.75
    áct
    -0.75
    POSITIVE LOGITS
     itself
    1.13
    =$_
    0.95
     này
    0.93
     مذ
    0.88
    นี้
    0.86
    ubu
    0.84
    óricos
    0.81
     моих
    0.80
     mentioned
    0.80
     bespoke
    0.80
    Activations Density 0.360%

    No Known Activations