© 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. 90976
    Prev
    Next
    INDEX
    Explanations

    ICANN Fees and Deleting

    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
    b
    0.55
    ב
    0.54
    eb
    0.50
     p
    0.49
    lenen
    0.47
     b
    0.46
     जब
    0.46
    ม
    0.46
    i
    0.45
    Í
    0.45
    POSITIVE LOGITS
     opportunità
    0.51
     duplicating
    0.49
     Updates
    0.48
    CURSOR
    0.47
     Deleg
    0.46
     Eurostile
    0.45
     conteúdo
    0.44
    िमी
    0.43
    实时
    0.43
     স্থাপত্য
    0.43
    Activations Density 0.003%

    No Known Activations