© 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. 177283
    Prev
    Next
    INDEX
    Explanations

    READY to write

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

    defining explanations and examples

    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
     Париж
    0.48
    HBO
    0.45
    体に
    0.45
    驍
    0.45
    ܵ
    0.44
    Salam
    0.43
     автоном
    0.43
    Antes
    0.42
     і
    0.42
     Elm
    0.42
    POSITIVE LOGITS
    __);
    0.51
     smears
    0.50
    ur
    0.48
     matcha
    0.47
     lessen
    0.45
    ahara
    0.45
    वटी
    0.45
    uere
    0.45
    phs
    0.45
     earths
    0.44
    Activations Density 0.000%

    No Known Activations