© 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. 31548
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific phrases

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

    assembly processing

    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
    ロス
    0.63
    ども
    0.52
    と
    0.52
    টিশ
    0.52
    ブランド
    0.52
     کہنے
    0.52
    Từ
    0.51
    雙
    0.51
    徂
    0.51
     سنة
    0.50
    POSITIVE LOGITS
    t
    0.57
    ur
    0.55
    gars
    0.54
     interviews
    0.54
    starts
    0.50
    hut
    0.50
     kir
    0.50
    isations
    0.50
     empires
    0.50
    ul
    0.49
    Activations Density 0.000%

    No Known Activations