© 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. 22704
    Prev
    Next
    INDEX
    Explanations

    names, locations, code, and specific entities

    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
     images
    0.53
    ,
    0.50
     scenes
    0.49
     seamlessly
    0.49
     colourful
    0.48
     and
    0.47
     for
    0.47
     পরিষেবা
    0.47
     wearable
    0.47
     connectivity
    0.46
    POSITIVE LOGITS
    樓
    0.51
     итоге
    0.50
     ಅಧ್ಯ
    0.47
    Nguyen
    0.47
    PhD
    0.46
    Roth
    0.45
    Natalie
    0.45
    彻底
    0.45
    Chase
    0.45
     ஆராய்ச்ச
    0.44
    Activations Density 0.007%

    No Known Activations