© 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. 22582
    Prev
    Next
    INDEX
    Explanations

    RM currency

    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
     olds
    0.43
    蕉
    0.40
    sprecher
    0.40
     tilapia
    0.38
     chirop
    0.38
    不大
    0.37
    恢
    0.37
     BNF
    0.37
     رکھے
    0.36
    Неза
    0.36
    POSITIVE LOGITS
     rigidity
    0.44
    芮
    0.43
    вобо
    0.42
     gul
    0.39
     Gul
    0.39
     उद्यम
    0.38
    ampling
    0.38
     viernes
    0.37
     громад
    0.37
    affaires
    0.37
    Activations Density 0.001%

    No Known Activations