© 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-262K
    7. 47774
    Prev
    Next
    INDEX
    Explanations

    head or root of data structures

    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_262k_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
     recipro
    0.43
     وجود
    0.43
    recursion
    0.43
     reciproc
    0.41
     Tsch
    0.41
     recursive
    0.40
    ❰
    0.40
     cereal
    0.39
    putation
    0.39
     carboxyl
    0.39
    POSITIVE LOGITS
    ίν
    0.46
    涜
    0.43
     любви
    0.42
     dirigido
    0.42
     dirigida
    0.41
    বাধিকার
    0.40
    чески
    0.40
    োষ
    0.40
    欧
    0.40
    质疑
    0.39
    Activations Density 0.003%

    No Known Activations