© 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. 10-GEMMASCOPE-RES-131K
    7. 80631
    Prev
    Next
    INDEX
    Explanations

    what ... for questions

    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
     alça
    -1.88
     protegido
    -1.59
     aguj
    -1.59
     parachoque
    -1.58
     sellado
    -1.57
    茘
    -1.55
     OGSÅ
    -1.54
     baseado
    -1.48
     contento
    -1.48
    ᐕ
    -1.48
    POSITIVE LOGITS
     to
    1.86
     but
    1.70
    —
    1.60
    ;
    1.56
     (
    1.55
    ↵↵
    1.45
    )
    1.41
     then
    1.39
     purpose
    1.38
    <em>
    1.37
    Activations Density 0.033%

    No Known Activations