© 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. 43288
    Prev
    Next
    INDEX
    Explanations

    multi-lingual entities and content

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

    melt your ice

    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
     ብዙውን
    0.49
    corpus
    0.46
     மற்றொரு
    0.45
     მიმოწერა
    0.45
     வெறும்
    0.44
    💉
    0.43
     Bald
    0.43
     பெறும்
    0.43
     Himalayan
    0.43
     باستخدام
    0.43
    POSITIVE LOGITS
     nonprofits
    0.47
    𝘀
    0.46
     निर्मला
    0.44
    щать
    0.43
    𝗶
    0.43
    िलं
    0.43
    𝗯
    0.42
    而且
    0.42
    ulins
    0.42
    𝗜
    0.42
    Activations Density 0.000%

    No Known Activations