© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14528
    Prev
    Next
    INDEX
    Explanations

    eminent figures and achievements

    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
     tornillos
    -1.61
    кзак
    -1.55
    푙
    -1.49
     tranſ
    -1.48
     schrijven
    -1.45
    擼
    -1.43
    kelt
    -1.41
     betek
    -1.41
     tirantes
    -1.41
    重點
    -1.40
    POSITIVE LOGITS
    )
    1.77
    s
    1.73
     during
    1.54
     on
    1.41
     should
    1.38
    왓
    1.36
     t
    1.34
     Unglück
    1.34
     at
    1.30
    1
    1.30
    Activations Density 0.033%

    No Known Activations