© 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. 55879
    Prev
    Next
    INDEX
    Explanations

    phrases within quotation marks

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

    explicit content discussion

    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
     tanti
    0.47
     寸
    0.46
    ColumnHeaders
    0.45
     winemaker
    0.43
     Middleware
    0.43
     histamine
    0.43
     '':
    0.42
     delimiter
    0.42
     Doesn
    0.42
     Linking
    0.42
    POSITIVE LOGITS
    urang
    0.53
    那边
    0.47
    𝓌
    0.47
    તે
    0.46
    ପ
    0.46
    थी
    0.46
    ט
    0.46
     wrecked
    0.45
    ùng
    0.45
     drifted
    0.45
    Activations Density 0.000%

    No Known Activations