© 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. 172394
    Prev
    Next
    INDEX
    Explanations

    refill tools

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

    Collie SVG files

    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
    dong
    0.54
    dex
    0.53
    dictionary
    0.51
    枚举
    0.49
    대
    0.47
    னாக
    0.47
    包
    0.47
    汇报
    0.47
    沟
    0.47
    δέ
    0.46
    POSITIVE LOGITS
     meglio
    0.47
     selezion
    0.47
     nước
    0.47
     தண்ணீர்
    0.46
     ultimo
    0.46
    znac
    0.46
     costruzione
    0.45
     Aussage
    0.45
     cinque
    0.44
     acqua
    0.44
    Activations Density 0.001%

    No Known Activations