© 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. 105738
    Prev
    Next
    INDEX
    Explanations

    version of

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

    configuration variables and parameters

    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
     Custom
    0.40
    setUp
    0.40
     Gamble
    0.38
    [^
    0.38
     Mond
    0.37
     astonishing
    0.37
    伴
    0.37
    대에
    0.37
    一条
    0.37
    ┅
    0.36
    POSITIVE LOGITS
     numérica
    0.54
     wartość
    0.47
     temperatura
    0.46
     tamanho
    0.46
     temperaturas
    0.45
     اندرو
    0.43
    Romans
    0.43
     relacionados
    0.43
     romans
    0.43
     jumlah
    0.42
    Activations Density 0.002%

    No Known Activations