© 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. 219283
    Prev
    Next
    INDEX
    Explanations

    his wife

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

    word list formatting

    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
     innymi
    0.41
     Otras
    0.41
     även
    0.40
     丶
    0.40
     inoltre
    0.40
     también
    0.39
     також
    0.39
     ankaŭ
    0.39
     bakteri
    0.38
     možno
    0.38
    POSITIVE LOGITS
    잔
    0.43
    ρά
    0.42
    Angleterre
    0.41
    England
    0.40
    setTime
    0.39
    Paris
    0.39
    Canada
    0.39
    लाना
    0.39
    ——
    0.39
    โต
    0.39
    Activations Density 0.009%

    No Known Activations