© 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. 249319
    Prev
    Next
    INDEX
    Explanations

    lists or general information following a noun

    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
     موسیقی
    0.56
    悪
    0.52
     exponer
    0.51
    音楽
    0.49
    由於
    0.49
    血压
    0.48
    歌詞
    0.47
     heeft
    0.47
    音乐
    0.47
    楽曲
    0.47
    POSITIVE LOGITS
    it
    0.60
    ai
    0.57
    in
    0.55
    ir
    0.55
    x
    0.55
    update
    0.54
    updated
    0.54
    em
    0.52
    ul
    0.49
    im
    0.49
    Activations Density 0.000%

    No Known Activations