© 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. 128991
    Prev
    Next
    INDEX
    Explanations

    class creation or update

    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
     and
    -2.06
     the
    -1.88
    ところに
    -1.82
    づけ
    -1.77
     their
    -1.67
    為に
    -1.67
     There
    -1.53
    でに
    -1.46
     Whether
    -1.44
     Since
    -1.42
    POSITIVE LOGITS
    <bos>
    1.82
    は
    1.63
    を
    1.62
    それも
    1.59
    
    1.53
    麻烦
    1.52
    階段
    1.52
     Grüßen
    1.48
    が
    1.47
    も
    1.46
    Activations Density 0.013%

    No Known Activations