© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10574
    Prev
    Next
    INDEX
    Explanations

    Valley of

    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
    vidla
    -1.52
    ཫ
    -1.39
    RANDOM
    -1.37
    تز
    -1.36
    ͇
    -1.33
    ]}>
    -1.32
     остальных
    -1.30
     gömlek
    -1.30
    kriegs
    -1.30
    ưới
    -1.29
    POSITIVE LOGITS
    -
    2.14
     of
    2.03
     than
    1.95
     then
    1.90
    [
    1.61
     Затем
    1.57
    ?
    1.56
     to
    1.48
     different
    1.48
    纔
    1.47
    Activations Density 0.050%

    No Known Activations