© 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. 87400
    Prev
    Next
    INDEX
    Explanations

    names and events

    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
     It
    -2.34
     That
    -2.27
     unable
    -1.98
    '
    -1.94
     are
    -1.88
    )"
    -1.86
    CEAN
    -1.80
     you
    -1.80
     meant
    -1.79
    that
    -1.77
    POSITIVE LOGITS
    铱
    1.91
     этим
    1.88
     нового
    1.84
     櫃
    1.73
    ۱۵
    1.71
    んですけど
    1.69
     ڤ
    1.68
    klaim
    1.68
    ujem
    1.66
    麻烦
    1.63
    Activations Density 0.000%

    No Known Activations