© 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. 24297
    Prev
    Next
    INDEX
    Explanations

    python typing imports

    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
    ભગ
    0.43
     जस्ट
    0.42
    तालों
    0.42
     පේශ
    0.41
     bactéri
    0.41
    糙
    0.41
    ረ
    0.40
     chút
    0.40
     ভারতীয়
    0.39
    😏
    0.39
    POSITIVE LOGITS
    ion
    0.42
     full
    0.42
    S
    0.41
    ional
    0.40
     reass
    0.39
     Capital
    0.39
     partisan
    0.39
     capitalization
    0.38
    ission
    0.38
    Class
    0.37
    Activations Density 0.000%

    No Known Activations