© 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. 47681
    Prev
    Next
    INDEX
    Explanations

    project discussions

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

    xml project definition

    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
    слежи
    0.53
    葶
    0.50
     Хоккей
    0.50
    浗
    0.50
    Pyrazole
    0.48
    ายเป็น
    0.48
    রোপ
    0.48
     кушымта
    0.47
    叕
    0.47
    зяй
    0.47
    POSITIVE LOGITS
    ia
    0.48
     fasci
    0.45
    ly
    0.44
     seas
    0.44
    breaking
    0.43
     fascia
    0.43
    variant
    0.42
    power
    0.42
     variant
    0.42
     vict
    0.42
    Activations Density 0.000%

    No Known Activations