© 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. 155076
    Prev
    Next
    INDEX
    Explanations

    visuals and places

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

    really, less

    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
     當
    0.52
     etiology
    0.47
     ያስፈል
    0.46
    旸
    0.46
     washable
    0.45
     prévention
    0.45
     显示
    0.45
     nourish
    0.45
     purpos
    0.44
     coexist
    0.44
    POSITIVE LOGITS
     Genres
    0.47
    Travel
    0.45
    虎
    0.44
    Genres
    0.43
     Bars
    0.43
    Genre
    0.43
     Postage
    0.42
    镣
    0.42
     Traveler
    0.41
     Tuning
    0.41
    Activations Density 0.005%

    No Known Activations