© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123682
    Prev
    Next
    INDEX
    Explanations

    faint magnitudes

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

    class, for, self, or structure

    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
    Negative Logits
    F
    0.45
     carve
    0.45
     jazy
    0.44
     pracy
    0.44
     curve
    0.43
     kart
    0.43
     curva
    0.42
     airbag
    0.42
     carving
    0.42
     Tyre
    0.42
    POSITIVE LOGITS
    ManagerPortal
    0.53
    と感じ
    0.50
    $&$-
    0.50
    与此同时
    0.49
     çünkü
    0.49
     क्योंकि
    0.48
     इसीलिए
    0.48
    最大限
    0.47
    黜
    0.47
     અમારી
    0.46
    Activations Density 0.001%

    No Known Activations