© 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. 233735
    Prev
    Next
    INDEX
    Explanations

    games and labels

    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
    别墅
    0.46
    찻
    0.44
    调研
    0.43
    争议
    0.43
    ंद्र
    0.42
     porter
    0.42
    鎚
    0.42
     porphy
    0.42
    抨
    0.41
    얏
    0.41
    POSITIVE LOGITS
    N
    0.48
    6
    0.47
    7
    0.46
    ل
    0.46
    8
    0.45
     females
    0.44
     <=
    0.44
    NSMutable
    0.44
    non
    0.43
    Non
    0.42
    Activations Density 0.000%

    No Known Activations