© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126555
    Prev
    Next
    INDEX
    Explanations

    header consistently includesSLAM allowsonly selldata into tables

    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
     prev
    0.50
     ACE
    0.47
     adventurer
    0.46
     conex
    0.46
     membro
    0.45
     cuya
    0.45
    は
    0.44
    會員
    0.43
    ประเภท
    0.43
     membre
    0.42
    POSITIVE LOGITS
    śni
    0.49
    formulas
    0.47
    norms
    0.47
    en
    0.47
    🎿
    0.46
    াকিস্ত
    0.46
    obarb
    0.46
    recycl
    0.45
    hoti
    0.45
    waste
    0.45
    Activations Density 0.002%

    No Known Activations