© 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. 40-GEMMASCOPE-2-RES-262K
    7. 221728
    Prev
    Next
    INDEX
    Explanations

    code inclusion paths

    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_40_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
     can
    0.49
    0.43
     just
    0.41
     in
    0.41
     lack
    0.40
    <strong>
    0.40
     shall
    0.39
     visit
    0.38
     final
    0.37
     slice
    0.37
    POSITIVE LOGITS
     formulae
    0.54
     fórmulas
    0.54
     parametros
    0.54
    defs
    0.52
    formulas
    0.52
     comuns
    0.51
    initions
    0.50
    溸
    0.50
     formules
    0.48
    參數
    0.48
    Activations Density 0.002%

    No Known Activations