© 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. 251297
    Prev
    Next
    INDEX
    Explanations

    about and must

    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
    COMMIT
    0.53
     manicure
    0.45
    treasure
    0.45
    Sweep
    0.44
     lustre
    0.44
    ඕ
    0.44
    commentaire
    0.43
    DECLARE
    0.43
    ی
    0.43
    topo
    0.43
    POSITIVE LOGITS
    ويه
    0.50
    ная
    0.48
    يس
    0.47
    وين
    0.47
     фильмов
    0.45
     фильмы
    0.44
     города
    0.44
    రగ
    0.43
    隔離
    0.43
    히려
    0.43
    Activations Density 0.000%

    No Known Activations