© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 15568
    Prev
    Next
    INDEX
    Explanations

    undo/fix

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    估
    0.54
     analogous
    0.54
     парази
    0.53
     appetizers
    0.52
    liminf
    0.52
    անք
    0.52
     जय
    0.51
     halftime
    0.50
     aislamiento
    0.50
    шке
    0.50
    POSITIVE LOGITS
     confront
    0.59
     ثابت
    0.59
     reunite
    0.59
    ở
    0.55
    Prove
    0.54
     confronts
    0.54
     smooth
    0.53
     இல்லாமல்
    0.52
     reun
    0.51
     avenge
    0.51
    Activations Density 0.039%

    No Known Activations