© 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. 111096
    Prev
    Next
    INDEX
    Explanations

    various languages

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

    deployment slot swap

    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
     )[
    0.48
     according
    0.48
     کون
    0.45
    iguation
    0.45
     menjel
    0.45
    ται
    0.44
    esu
    0.44
    '[
    0.43
     حسب
    0.43
    라는
    0.43
    POSITIVE LOGITS
     চাহিয়া
    0.48
     серь
    0.47
    梅里
    0.46
    国内外
    0.46
     चिंत
    0.45
     குறிப்பாக
    0.44
     крупней
    0.44
     অধিনায়ক
    0.43
     इलाकों
    0.43
    打算
    0.42
    Activations Density 0.000%

    No Known Activations