© 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. 29849
    Prev
    Next
    INDEX
    Explanations

    No, good

    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
    ョン
    0.45
    нология
    0.44
    པ
    0.44
    льні
    0.44
    罢了
    0.43
    р
    0.43
    е
    0.42
    PLL
    0.42
    Ps
    0.42
     финан
    0.41
    POSITIVE LOGITS
     Tai
    0.46
     Fet
    0.44
     雨
    0.44
     وس
    0.42
     Wine
    0.41
     stabilize
    0.41
     automate
    0.41
     马
    0.41
     Stra
    0.40
    自動
    0.40
    Activations Density 0.014%

    No Known Activations