© 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. 99802
    Prev
    Next
    INDEX
    Explanations

    words followed by descriptions

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

    meaning creation

    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
    s
    0.70
     ()
    0.54
     Read
    0.54
    س
    0.54
    ّ
    0.48
     ().
    0.47
    ই
    0.47
    is
    0.46
    ly
    0.46
     TIL
    0.46
    POSITIVE LOGITS
     제곱
    0.55
    を受け
    0.49
    ยายาม
    0.49
     λόγω
    0.48
     пусть
    0.47
     arba
    0.47
    쭤
    0.46
    štu
    0.46
     ګرځنده
    0.46
     одну
    0.46
    Activations Density 0.001%

    No Known Activations