© 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. 127354
    Prev
    Next
    INDEX
    Explanations

    lever arm

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

    calculation, commercial, counterfeit

    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
    Après
    0.47
    ('/');
    0.46
    нта
    0.46
    ብስብ
    0.45
    у
    0.45
    随时
    0.44
    өх
    0.44
    ופ
    0.44
    輿
    0.44
    지에
    0.43
    POSITIVE LOGITS
     محاسبه
    0.49
     usu
    0.47
    MATRIX
    0.47
    matrix
    0.47
     formul
    0.46
     اهو
    0.44
     公式
    0.44
     chhoti
    0.44
    Billboard
    0.44
     કર
    0.43
    Activations Density 0.001%

    No Known Activations