© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 170072
    Prev
    Next
    INDEX
    Explanations

    contract limitations

    np_acts-logits-general · gemini-2.5-flash-lite

    reporting instructor utilization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ant
    0.53
    ell
    0.52
    ne
    0.51
    i
    0.50
     Mass
    0.48
     Mobile
    0.47
    e
    0.46
    ur
    0.46
    ak
    0.46
     Bit
    0.46
    POSITIVE LOGITS
    WholeProgram
    0.49
     ಅವನು
    0.48
    ῷ
    0.47
    뒤
    0.47
    καν
    0.47
     cinese
    0.47
    鼗
    0.47
    goatee
    0.46
    はもちろん
    0.46
    ক্ষেপে
    0.46
    Activations Density 0.000%

    No Known Activations