© 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. 22798
    Prev
    Next
    INDEX
    Explanations

    lists following words

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

    wife, Arthur, Tunnel, Microwave, oven, school, solar

    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
    ilium
    0.48
    ROWS
    0.47
    RowCount
    0.45
    TextField
    0.45
    FrameID
    0.43
     infert
    0.43
    agina
    0.41
    ;$
    0.41
    Rows
    0.40
    Benzo
    0.40
    POSITIVE LOGITS
     victoire
    0.50
    的学生
    0.47
     முதல்
    0.47
     consacré
    0.47
    ி
    0.47
     Study
    0.46
     ➤
    0.46
     presque
    0.45
    সম্পাদকীয়
    0.45
     জেগে
    0.45
    Activations Density 0.000%

    No Known Activations