© 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. 152311
    Prev
    Next
    INDEX
    Explanations

    or the comma

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

    legal, medical, and technical terms

    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
    נ
    0.52
    ಮ
    0.48
     цер
    0.48
    Appellant
    0.48
    Expiry
    0.47
    Rets
    0.47
    BadRequest
    0.46
    Anast
    0.46
    Fen
    0.46
    나
    0.45
    POSITIVE LOGITS
    ene
    0.53
    angani
    0.49
     structural
    0.48
    етра
    0.47
    iket
    0.46
     idiosyncratic
    0.46
    eth
    0.44
    anya
    0.44
    aron
    0.44
     coma
    0.44
    Activations Density 0.001%

    No Known Activations