© 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. 8033
    Prev
    Next
    INDEX
    Explanations

    python code

    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
    辊
    0.29
     ponctuées
    0.29
     répar
    0.27
     ĝi
    0.27
     Repair
    0.27
     repairing
    0.27
    ൂട്ട
    0.27
     oppure
    0.26
    Callories
    0.26
    پیگنڈ
    0.26
    POSITIVE LOGITS
    <0x0D>
    0.29
    ，
    0.29
     h
    0.29
    k
    0.29
    scales
    0.27
    द
    0.27
    ↵
    0.27
    h
    0.26
    ↵↵
    0.26
    у
    0.26
    Activations Density 0.122%

    No Known Activations