© 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. 158304
    Prev
    Next
    INDEX
    Explanations

    parts, objects, members, options

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

    physical actions and body parts

    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
    !
    0.49
     فلسطين
    0.48
    ?
    0.48
    ﻌ
    0.48
    మ
    0.46
     tokenizer
    0.46
     AND
    0.44
     millimeter
    0.43
    娘
    0.43
    真的很
    0.43
    POSITIVE LOGITS
     sabit
    0.48
    cattle
    0.47
    abat
    0.46
    砣
    0.46
    гү
    0.46
    boom
    0.46
    genCode
    0.46
    flav
    0.45
    OID
    0.45
     Established
    0.45
    Activations Density 0.001%

    No Known Activations