© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51390
    Prev
    Next
    INDEX
    Explanations

    function setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ።
    0.47
     بِ
    0.45
     boyfriend
    0.44
     решила
    0.44
     Slides
    0.43
     Highlight
    0.43
     Bc
    0.43
     histogram
    0.43
     केश
    0.43
     علیہ
    0.43
    POSITIVE LOGITS
    質
    0.48
    資
    0.48
    利用
    0.45
    約
    0.44
    の間
    0.44
     avem
    0.43
    長期
    0.43
     ਸਰ
    0.43
    長
    0.43
    其他
    0.43
    Activations Density 0.003%

    No Known Activations