© 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. 11116
    Prev
    Next
    INDEX
    Explanations

    quantities or percentages

    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
     pierws
    -1.55
     adhesivo
    -1.45
    เดียว
    -1.39
     wohin
    -1.37
     Теперь
    -1.37
    навли
    -1.33
     caucho
    -1.33
    .
    -1.31
    分支
    -1.31
     partiellement
    -1.30
    POSITIVE LOGITS
     your
    1.65
     for
    1.63
     all
    1.60
     on
    1.41
     /
    1.40
     overall
    1.37
     conceivable
    1.34
    t
    1.34
     circa
    1.34
     when
    1.34
    Activations Density 0.020%

    No Known Activations