© 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. 26362
    Prev
    Next
    INDEX
    Explanations

    resource links, button large, fountain of

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

    contrasting specialized vs. general

    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
    '
    0.49
    ﺭ
    0.46
     يه
    0.46
     glial
    0.45
     capillary
    0.45
    network
    0.43
    на
    0.43
     deposit
    0.42
    portfolio
    0.42
    timeLeft
    0.42
    POSITIVE LOGITS
    壮
    0.50
    聸
    0.47
    കര്‍
    0.46
     vv
    0.44
    rendre
    0.44
    ➼
    0.44
    undu
    0.43
    ଜ
    0.43
    不断
    0.43
     dévo
    0.43
    Activations Density 0.000%

    No Known Activations