© 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. 112298
    Prev
    Next
    INDEX
    Explanations

    HTML link attributes

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

    documentation links

    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
    (*(
    0.43
    ercises
    0.41
    Decorative
    0.40
    महिलाओं
    0.40
    ński
    0.39
    Women
    0.39
    ських
    0.38
    ESSMENT
    0.38
    庆祝
    0.38
    थमिक
    0.38
    POSITIVE LOGITS
     sampai
    0.44
     garantía
    0.43
    󰡕
    0.42
    িন্দু
    0.42
    ទ្ធ
    0.41
     cuál
    0.41
     toj
    0.41
     cuero
    0.41
     cuándo
    0.40
     forfeiture
    0.39
    Activations Density 0.001%

    No Known Activations