© 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. 200979
    Prev
    Next
    INDEX
    Explanations

    extra t-shirt/sweater

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

    high capacity, score, common

    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
    áciu
    0.53
    ne
    0.51
    ’
    0.51
    ati
    0.50
    atien
    0.47
     میتوان
    0.46
    யின்
    0.45
    ani
    0.45
    atu
    0.44
    ana
    0.44
    POSITIVE LOGITS
    czas
    0.55
     Darrell
    0.54
     पीपल
    0.54
    Ժ
    0.53
    Ｊ
    0.49
    友
    0.49
    ジム
    0.48
    दमी
    0.48
     ruso
    0.48
     काउंस
    0.46
    Activations Density 0.000%

    No Known Activations