© 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. 16-GEMMASCOPE-2-RES-262K
    7. 30014
    Prev
    Next
    INDEX
    Explanations

    elusive concepts and entities

    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_16_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
    la
    0.63
    ض
    0.58
    تو
    0.56
    لي
    0.54
     enorm
    0.53
    惡
    0.53
     odio
    0.52
     frem
    0.51
     hemispheres
    0.51
     insc
    0.50
    POSITIVE LOGITS
    ۰
    0.93
    ł
    0.82
    ри
    0.80
     که
    0.77
    can
    0.76
    olni
    0.76
    ong
    0.75
    ।।
    0.73
    ementara
    0.73
    に
    0.73
    Activations Density 0.001%

    No Known Activations