© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 95275
    Prev
    Next
    INDEX
    Explanations

    snow, condensation, MB, kitten, digging

    np_acts-logits-general · gemini-2.5-flash-lite

    lists, definitions, properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recto
    0.55
     ඔහු
    0.49
    otherArgs
    0.48
    vient
    0.46
     bana
    0.46
     φ
    0.46
     CORS
    0.46
     아버지
    0.45
    clonal
    0.45
    computed
    0.44
    POSITIVE LOGITS
    лина
    0.47
    列表
    0.47
    名单
    0.46
    榜
    0.45
     শতাংশ
    0.44
     paints
    0.44
    ﺀ
    0.43
     registr
    0.43
    桿
    0.43
     מיט
    0.42
    Activations Density 0.000%

    No Known Activations