© 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. 128860
    Prev
    Next
    INDEX
    Explanations

    aggressive refining

    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
    उ
    0.52
    ری
    0.52
    But
    0.46
    به
    0.43
    이
    0.43
    気になる
    0.43
    ক
    0.43
     jelas
    0.43
    ఇ
    0.43
    aments
    0.42
    POSITIVE LOGITS
    того
    0.55
     máxim
    0.47
    етка
    0.45
     Éireann
    0.44
    gomery
    0.44
    embl
    0.44
     Usuarios
    0.43
     తమ
    0.43
     Polytechnic
    0.42
    etva
    0.42
    Activations Density 0.004%

    No Known Activations