© 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. 8407
    Prev
    Next
    INDEX
    Explanations

    GLSL, IDL, wasm, XSL, LSL

    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
    ཋ
    -2.52
     They
    -2.36
    ねー
    -2.33
    ねぇ
    -2.17
    幾天
    -2.13
    </td>
    -2.08
     labeled
    -2.05
     δεν
    -2.03
    旁邊
    -2.02
    鱨
    -1.99
    POSITIVE LOGITS
    in
    3.39
    </strong>
    2.72
    on
    2.70
    蹰
    2.58
    as
    2.56
    she
    2.33
    section
    2.20
    but
    2.14
     adventures
    2.11
    it
    2.06
    Activations Density 0.009%

    No Known Activations