© 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. 200228
    Prev
    Next
    INDEX
    Explanations

    life-altering injury processing

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

    before or after clauses

    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
    𒉺
    0.52
     Pér
    0.49
    ský
    0.48
     perchè
    0.47
     原因
    0.46
     Juárez
    0.45
    ſelf
    0.45
    ühlt
    0.45
     ಮಾ
    0.44
     ò
    0.44
    POSITIVE LOGITS
    van
    0.46
    of
    0.44
     publiques
    0.43
     librarians
    0.43
     handles
    0.43
     celles
    0.42
     checkers
    0.42
    ST
    0.41
     bodies
    0.41
     contraception
    0.41
    Activations Density 0.001%

    No Known Activations