© 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-65K
    7. 52038
    Prev
    Next
    INDEX
    Explanations

    details about files

    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_65k_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
     मांग
    0.46
     спорт
    0.45
     кожу
    0.44
     සී
    0.44
     ски
    0.44
     हार्मोन
    0.44
    잭
    0.44
     negotiating
    0.43
     соли
    0.42
     새로운
    0.42
    POSITIVE LOGITS
     en
    0.54
     wont
    0.48
     ment
    0.47
    a
    0.47
     für
    0.46
     sesuai
    0.46
     Opp
    0.45
     perchè
    0.45
     ums
    0.44
     para
    0.44
    Activations Density 0.003%

    No Known Activations