© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 57726
    Prev
    Next
    INDEX
    Explanations

    the default, across the, fairly even

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

    grams, months, Mecca, correctly, ship, imprisonment

    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
     imagen
    0.55
     to
    0.54
     O
    0.54
     GAR
    0.54
     MAG
    0.50
     FOR
    0.50
     HUAWEI
    0.49
     WINTER
    0.49
     gute
    0.48
     scrapbook
    0.48
    POSITIVE LOGITS
    ρίου
    0.51
    よう
    0.48
    골
    0.47
    숴
    0.47
    ள்ள
    0.46
    롤
    0.45
    Since
    0.45
    getWorld
    0.44
    캄
    0.43
    šću
    0.43
    Activations Density 0.000%

    No Known Activations