© 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. 41-GEMMASCOPE-2-RES-262K
    7. 98855
    Prev
    Next
    INDEX
    Explanations

    Reverse wrist curls

    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_all/layer_41_width_262k_l0_big
    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
     communic
    0.41
     komunik
    0.40
     Plante
    0.39
     informat
    0.39
    娌
    0.38
     terapé
    0.37
    玉
    0.37
     pensée
    0.36
     procé
    0.36
    悔
    0.36
    POSITIVE LOGITS
    Glasgow
    0.71
     Glasgow
    0.67
     glas
    0.50
    glas
    0.50
     Glas
    0.50
    Glas
    0.50
    Controller
    0.43
    tochrome
    0.40
     Clyde
    0.40
    aza
    0.39
    Activations Density 0.000%

    No Known Activations