© 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. 113466
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations

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

    distinct organizations, Long for

    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
     محاضرات
    0.60
     ಅಪಾಯ
    0.58
     ಮೇ
    0.57
     инвести
    0.57
     আইডি
    0.56
     計算
    0.56
     골
    0.55
     פּ
    0.55
     いっ
    0.55
     ಕ್ಯಾ
    0.55
    POSITIVE LOGITS
    a
    0.69
    <0x0D>
    0.55
    ;
    0.54
     Period
    0.52
    d
    0.52
    u
    0.51
    i
    0.51
     Picture
    0.50
    o
    0.50
    0
    0.50
    Activations Density 0.000%

    No Known Activations