© 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. 74826
    Prev
    Next
    INDEX
    Explanations

    disabilities, type, understand, makes

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

    initialization and state representation

    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
    뭡
    0.48
    ើ
    0.46
     rửa
    0.44
     cí
    0.43
     pribli
    0.43
     गाली
    0.43
    훤
    0.43
     bổ
    0.43
    كمل
    0.42
     washes
    0.42
    POSITIVE LOGITS
     victories
    0.49
    няют
    0.46
    örper
    0.44
    ipe
    0.43
     Timurtaş
    0.43
    ləşdir
    0.43
     seeds
    0.43
    selves
    0.43
     Stade
    0.42
    ricted
    0.42
    Activations Density 0.000%

    No Known Activations