© 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. 24012
    Prev
    Next
    INDEX
    Explanations

    look up

    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
    {
    -1.88
    taya
    -1.45
    Università
    -1.44
     тот
    -1.38
     mayo
    -1.38
    jenige
    -1.34
     was
    -1.34
     возможно
    -1.33
     sieben
    -1.33
    </h5>
    -1.31
    POSITIVE LOGITS
     utilizzo
    1.65
    勦
    1.63
     impegno
    1.50
    慤
    1.49
    龌
    1.48
    after
    1.48
    useNewUrlParser
    1.47
    ll
    1.47
    also
    1.46
    there
    1.45
    Activations Density 0.016%

    No Known Activations