© 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. 143892
    Prev
    Next
    INDEX
    Explanations

    shipping, orders, possibility, process

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

    polished writing

    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
    ль
    0.54
    видно
    0.49
    листи
    0.47
    짊
    0.46
    ון
    0.44
    рат
    0.43
    ة
    0.43
    ני
    0.42
    בין
    0.42
    ای
    0.42
    POSITIVE LOGITS
    to
    0.47
     transportation
    0.45
     newborns
    0.45
     surgery
    0.44
    times
    0.43
     glare
    0.42
    ######
    0.42
     अवस्था
    0.42
     butter
    0.42
     tím
    0.41
    Activations Density 0.002%

    No Known Activations