© 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-16K
    7. 11907
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

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

    numbers separated by commas

    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_16k_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
    喿
    0.37
    薜
    0.35
    এবং
    0.35
     *\
    0.35
    espère
    0.35
    ریز
    0.34
    rž
    0.34
    不同
    0.34
    iyordu
    0.33
    和一个
    0.33
    POSITIVE LOGITS
     T
    0.41
     see
    0.41
     rafters
    0.40
     for
    0.40
     deu
    0.39
     seem
    0.39
     LA
    0.39
     Bh
    0.38
     judicious
    0.38
     Th
    0.38
    Activations Density 0.027%

    No Known Activations