© 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. 251764
    Prev
    Next
    INDEX
    Explanations

    foreign language or descriptive words

    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
    ミックス
    0.54
    рий
    0.49
    のか
    0.49
    ๋า
    0.46
    喫
    0.46
     руху
    0.46
     माझा
    0.45
    弥
    0.45
    де
    0.45
    つく
    0.45
    POSITIVE LOGITS
     Farbe
    0.46
     unintentionally
    0.45
     poked
    0.44
     fárm
    0.44
     estilo
    0.44
     satisfactor
    0.43
     Aesthetics
    0.43
     acceso
    0.43
     usadas
    0.42
     Kennt
    0.42
    Activations Density 0.001%

    No Known Activations