© 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. 46603
    Prev
    Next
    INDEX
    Explanations

    marches

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

    story behind

    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
    ül
    0.49
    ọt
    0.48
    rays
    0.48
    öl
    0.48
    ági
    0.48
    acia
    0.47
    аз
    0.46
    ≤
    0.46
    Toc
    0.46
     fxe
    0.46
    POSITIVE LOGITS
     marches
    0.52
     marche
    0.48
     \
    0.46
     march
    0.45
     imperfect
    0.45
    クー
    0.44
    次は
    0.44
    封
    0.44
     allegedly
    0.43
     marched
    0.43
    Activations Density 0.000%

    No Known Activations