© 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. 68899
    Prev
    Next
    INDEX
    Explanations

    Q&A answers

    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
    despite
    -1.62
     legendar
    -1.59
     pérd
    -1.53
     juſ
    -1.50
     sélections
    -1.49
     despi
    -1.48
     contempl
    -1.47
     blessure
    -1.47
    ギュア
    -1.45
    considering
    -1.45
    POSITIVE LOGITS
     only
    2.02
     those
    1.96
     always
    1.88
     there
    1.81
     these
    1.74
     in
    1.73
     with
    1.66
     required
    1.63
     often
    1.63
     ONLY
    1.62
    Activations Density 0.192%

    No Known Activations