© 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. 122120
    Prev
    Next
    INDEX
    Explanations

    star reviewsLotionRochester

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

    required or equivalent comments

    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
    \'
    0.47
    fla
    0.46
     TREND
    0.45
    ḳ
    0.45
     scoperta
    0.44
     অভ
    0.43
    čiau
    0.43
     విద్య
    0.43
     perek
    0.43
     di
    0.42
    POSITIVE LOGITS
    ле
    0.54
    د
    0.52
    연
    0.51
     formularios
    0.49
    죄
    0.49
    讵
    0.49
    куда
    0.48
    ע
    0.48
    រួម
    0.48
    ის
    0.48
    Activations Density 0.000%

    No Known Activations