© 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. 87533
    Prev
    Next
    INDEX
    Explanations

    beginning to relieve

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

    rate than, you want, not a, which reduce, Load existing, Pollution Impacts, restricted keywords, Provide advice

    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
     знаходиться
    0.59
    理
    0.51
     자동
    0.48
    banam
    0.48
     presentó
    0.48
    quero
    0.48
     無料
    0.47
    年
    0.47
     може
    0.47
    '।
    0.47
    POSITIVE LOGITS
    aw
    0.45
    0
    0.45
     Operation
    0.45
    the
    0.44
    br
    0.44
     procédés
    0.43
    gee
    0.42
    jud
    0.42
     Magnitude
    0.42
     re
    0.41
    Activations Density 0.000%

    No Known Activations