© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 67502
    Prev
    Next
    INDEX
    Explanations

    in the

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

    text splitter

    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
    exemple
    0.53
    원본파일명
    0.50
    ሽታ
    0.49
    équipement
    0.47
     eigent
    0.47
     liberd
    0.47
    ᕝ
    0.47
    льнявыя
    0.47
     वैश्विक
    0.46
     ген
    0.46
    POSITIVE LOGITS
     Korean
    0.55
     Does
    0.54
     N
    0.51
     Katherine
    0.50
     M
    0.50
     Mall
    0.49
     May
    0.47
     Tomorrow
    0.47
     Recipes
    0.47
     WeChat
    0.47
    Activations Density 0.004%

    No Known Activations