© 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. 33930
    Prev
    Next
    INDEX
    Explanations

    essential foundation of

    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
    ereo
    0.37
    എ
    0.36
    bigsqcup
    0.35
    ウル
    0.35
    ம்தான்
    0.35
    ادي
    0.34
     людьми
    0.34
    ɩ
    0.34
    রাট
    0.33
     هنگ
    0.33
    POSITIVE LOGITS
    一切
    0.45
    अधिकांश
    0.42
    នៃការ
    0.42
     of
    0.41
     ofthe
    0.41
     Inequality
    0.41
     véritables
    0.41
     अधिकांश
    0.40
    tted
    0.40
     Grundlage
    0.40
    Activations Density 0.015%

    No Known Activations