© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113816
    Prev
    Next
    INDEX
    Explanations

    several shapes

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

    availability, compensation, or descriptions

    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
     nghệ
    0.51
     giá
    0.50
    对于
    0.50
     选择
    0.49
     吴
    0.48
     진
    0.48
     đỉnh
    0.47
     gên
    0.47
    惀
    0.47
     ق
    0.46
    POSITIVE LOGITS
    fog
    0.47
    ai
    0.42
     bureaucrats
    0.42
    urant
    0.42
    inationals
    0.41
    꼽
    0.39
     perceptual
    0.39
    ibbean
    0.39
     Tho
    0.39
    ὺς
    0.38
    Activations Density 0.001%

    No Known Activations