© 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. 90878
    Prev
    Next
    INDEX
    Explanations

    swimming in water

    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
     мебель
    0.56
     повы
    0.50
     вектор
    0.47
     {{-
    0.47
    もら
    0.46
    軌
    0.46
    ار
    0.45
    дать
    0.45
     немно
    0.45
     darle
    0.45
    POSITIVE LOGITS
    రకు
    0.42
    TAT
    0.42
    ﻚ
    0.41
    WUE
    0.41
    爱情
    0.40
    ijuana
    0.40
    ijdens
    0.39
     Raceway
    0.39
    ivering
    0.39
     affair
    0.38
    Activations Density 0.003%

    No Known Activations