© 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. 198340
    Prev
    Next
    INDEX
    Explanations

    divorced type

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

    WordPress Plugin

    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
    W
    0.56
    нансо
    0.51
    フォルト
    0.50
     inclinations
    0.50
    K
    0.50
    makeConstraints
    0.49
     escolher
    0.46
    DUC
    0.46
    раху
    0.46
    とても
    0.45
    POSITIVE LOGITS
    elt
    0.47
    }");
    0.45
    rotor
    0.45
    浆
    0.44
     Lambert
    0.44
     PackageManager
    0.43
    ส่ง
    0.43
     hamilton
    0.43
     lidí
    0.43
     Beaver
    0.42
    Activations Density 0.001%

    No Known Activations