© 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. 1736
    Prev
    Next
    INDEX
    Explanations

    recommend or instrumental

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

    data storage

    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
    觀眾
    0.32
    戲
    0.30
     lễ
    0.30
     ४
    0.30
    癹
    0.29
     নিন্দ
    0.29
    覤
    0.29
    hattim
    0.29
     asuntos
    0.29
    䚲
    0.29
    POSITIVE LOGITS
    А
    0.28
    /
    0.28
    A
    0.28
    C
    0.28
    R
    0.28
    ram
    0.27
    Ac
    0.27
    *
    0.27
    To
    0.27
    о
    0.27
    Activations Density 0.150%

    No Known Activations