© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63039
    Prev
    Next
    INDEX
    Explanations

    what followed by the

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

    mysterious option why using

    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
    铄
    0.47
     Recipes
    0.46
    atas
    0.46
     minh
    0.45
    ச்சல்
    0.45
     강의
    0.44
     Immunology
    0.43
     recipes
    0.43
     خاص
    0.43
     تا
    0.43
    POSITIVE LOGITS
    ΟΥ
    0.50
    \}$
    0.50
    千萬
    0.49
    ⎛
    0.48
    ণী
    0.47
    deque
    0.47
    펜
    0.47
     magari
    0.46
    リエ
    0.45
    dens
    0.45
    Activations Density 0.000%

    No Known Activations