© 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. 39950
    Prev
    Next
    INDEX
    Explanations

    shoot your shot

    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
    after
    -2.27
    硯
    -1.73
    礎
    -1.73
    闽
    -1.64
    浙
    -1.63
    of
    -1.59
    臻
    -1.59
    🌊
    -1.59
     после
    -1.58
     этом
    -1.58
    POSITIVE LOGITS
    </i>
    2.53
     geplant
    2.17
     gewiß
    2.13
    '
    2.08
    ↵
    2.03
     vorigen
    1.99
    ꜆
    1.93
     festge
    1.89
    鸸
    1.88
     zwanzig
    1.85
    Activations Density 0.021%

    No Known Activations