© 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. 10-GEMMASCOPE-RES-131K
    7. 22278
    Prev
    Next
    INDEX
    Explanations

    way to, common vocabulary, route through, tools to, basis for, additional opportunity, method for, modality for, strategy to, form of

    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_10/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
     there
    -2.34
     it
    -2.22
    there
    -1.88
    There
    -1.74
     There
    -1.63
     theres
    -1.46
     說
    -1.23
     هستم
    -1.23
    It
    -1.23
     recently
    -1.23
    POSITIVE LOGITS
     for
    2.50
     to
    1.91
     ۱۸
    1.55
     ۱۱
    1.55
     ۱۵
    1.52
    ())));
    1.41
     både
    1.40
     ۱۳
    1.38
    /}{
    1.34
     ۱۷
    1.34
    Activations Density 0.162%

    No Known Activations