© 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. 8419
    Prev
    Next
    INDEX
    Explanations

    units per

    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
     служба
    0.39
     серви
    0.37
    馔
    0.37
    精华
    0.36
     प्रत्येक
    0.36
     тариф
    0.36
    रीबन
    0.35
    각
    0.34
    лишком
    0.34
     решение
    0.34
    POSITIVE LOGITS
    per
    0.42
    %,
    0.39
    b
    0.39
    n
    0.38
    -
    0.38
     per
    0.36
    m
    0.36
    k
    0.35
    p
    0.35
     units
    0.35
    Activations Density 0.029%

    No Known Activations