© 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. 126768
    Prev
    Next
    INDEX
    Explanations

    politician names

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

    conjunction connecting listed items

    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
    '
    0.56
    0.55
    ird
    0.50
     mirip
    0.45
     thêm
    0.45
    ọ
    0.45
     của
    0.43
     society
    0.43
    ighth
    0.42
     leur
    0.42
    POSITIVE LOGITS
    ान्स
    0.48
    ভাগের
    0.47
    ♗
    0.47
    পশ্চ
    0.46
    ◞
    0.46
    פור
    0.45
    графии
    0.44
    周知
    0.44
    嬿
    0.44
    堃
    0.44
    Activations Density 0.001%

    No Known Activations