© 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. 119669
    Prev
    Next
    INDEX
    Explanations

    give to others

    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
     the
    -1.85
     In
    -1.75
     arī
    -1.63
     or
    -1.59
     for
    -1.59
    ᱾
    -1.46
     their
    -1.45
    ↵
    -1.45
    тели
    -1.42
     as
    -1.41
    POSITIVE LOGITS
    Might
    1.75
    Nicht
    1.70
    THERE
    1.70
    肫
    1.59
     ouvre
    1.57
     presque
    1.57
    镲
    1.57
     préparer
    1.54
    ÄT
    1.53
     můžete
    1.52
    Activations Density 0.033%

    No Known Activations