© 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. 99296
    Prev
    Next
    INDEX
    Explanations

    legalize accommodation update

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

    provides a

    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
     제조
    0.51
     کور
    0.48
     어린
    0.46
     Belling
    0.46
     Damon
    0.46
     ತಯಾರ
    0.45
     про
    0.44
    접
    0.44
     доступ
    0.44
     Cub
    0.43
    POSITIVE LOGITS
    ew
    0.55
    el
    0.53
    церт
    0.50
    ুয়া
    0.48
     legalize
    0.48
    umal
    0.47
    వా
    0.47
    eau
    0.46
    elter
    0.46
    ASIA
    0.46
    Activations Density 0.000%

    No Known Activations