© 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. 84286
    Prev
    Next
    INDEX
    Explanations

    Floyd Mayweather

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

    supporting, visiting, MMS dataset, Fire TV, understanding, smtp, liter jug, bit

    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
    肐
    0.50
    描述
    0.47
    хва
    0.46
    x
    0.45
    ประกัน
    0.45
    Individuals
    0.43
    ANDER
    0.43
    ఘ
    0.43
    稃
    0.42
    个体
    0.42
    POSITIVE LOGITS
     cáo
    0.48
     cartera
    0.47
     chăm
    0.47
     たち
    0.47
     totalidad
    0.46
     señal
    0.46
     କ
    0.45
     chauss
    0.45
    aży
    0.45
     Букмекердик
    0.44
    Activations Density 0.000%

    No Known Activations