© 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. 35370
    Prev
    Next
    INDEX
    Explanations

    drawing shapes

    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
    ⣀
    0.46
    ⠀⠀
    0.44
    ায়ের
    0.42
     complication
    0.38
    esség
    0.37
     Versch
    0.37
     Fears
    0.37
     komplik
    0.36
    })-\
    0.35
     luôn
    0.35
    POSITIVE LOGITS
    sembled
    0.40
    [[
    0.36
    ionalmente
    0.35
    AT
    0.34
    bigskip
    0.34
     우리가
    0.33
     চলুন
    0.33
     inzwischen
    0.33
    <0x81>
    0.33
     flanked
    0.33
    Activations Density 0.017%

    No Known Activations