© 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. 14903
    Prev
    Next
    INDEX
    Explanations

    find something surprising or strange

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

    find + reflexive pronoun

    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
    ور
    0.82
    ният
    0.79
    يز
    0.77
    ويل
    0.75
    氙
    0.72
    ко
    0.71
    ր
    0.71
    ري
    0.70
    но
    0.70
    ле
    0.69
    POSITIVE LOGITS
    in
    1.01
    af
    0.79
     out
    0.77
     it
    0.76
     find
    0.76
    at
    0.76
    ა
    0.75
    ierta
    0.73
    r
    0.71
    a
    0.71
    Activations Density 0.126%

    No Known Activations