© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8344
    Prev
    Next
    INDEX
    Explanations

    forum posts

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

    URLs with / characters

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     \\
    0.45
     cholest
    0.40
    龶
    0.40
    ﾃ
    0.39
    の
    0.39
     represented
    0.38
     exemplifies
    0.37
     inequalities
    0.37
     exf
    0.37
     cumul
    0.37
    POSITIVE LOGITS
    点头
    0.46
    .[/
    0.45
    এটা
    0.44
    Sure
    0.44
    这话
    0.44
    论坛
    0.43
    点击
    0.43
     সেটা
    0.42
    Passport
    0.40
    Компания
    0.39
    Activations Density 0.253%

    No Known Activations