© 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. 162133
    Prev
    Next
    INDEX
    Explanations

    kick taken, searched for

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

    search volume indicators

    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
     чемпионате
    0.44
     попыта
    0.43
    ULS
    0.42
    темати
    0.41
    Motivation
    0.41
    滪
    0.40
    联网
    0.40
    Опера
    0.40
    timepoint
    0.40
    辊
    0.40
    POSITIVE LOGITS
     naturais
    0.53
     devido
    0.50
     revered
    0.49
     với
    0.49
     elf
    0.49
    ٹ
    0.47
     with
    0.47
     pesquisas
    0.47
     Ero
    0.46
    t
    0.46
    Activations Density 0.001%

    No Known Activations