© 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. 102281
    Prev
    Next
    INDEX
    Explanations

    equivalent to

    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
    i
    -3.08
     The
    -2.95
     delightfully
    -2.86
     decidedly
    -2.80
    o
    -2.75
    みたら
    -2.73
    癭
    -2.70
    终于
    -2.63
    or
    -2.55
     deliciously
    -2.47
    POSITIVE LOGITS
    нутрен
    3.14
     tries
    3.11
     That
    3.05
     strives
    2.97
    酲
    2.91
     touted
    2.88
    尛
    2.81
    ୌ
    2.78
    陞
    2.75
     parís
    2.72
    Activations Density 0.004%

    No Known Activations