© 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. 204865
    Prev
    Next
    INDEX
    Explanations

    world increasingly, Tiber smiled, exam unlike

    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
    Վ
    0.47
    am
    0.46
    \%
    0.46
     felicit
    0.45
    m
    0.45
     ഏറ്റ
    0.44
    ereo
    0.44
     vutt
    0.43
    G
    0.43
    ('%
    0.43
    POSITIVE LOGITS
    сіння
    0.52
     Lottery
    0.46
    ObjectUnderTest
    0.44
     एडम
    0.42
     perk
    0.40
     Reward
    0.40
    اهرة
    0.40
     copertura
    0.40
    ̶
    0.40
    ية
    0.40
    Activations Density 0.003%

    No Known Activations