© 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. 48059
    Prev
    Next
    INDEX
    Explanations

    defining conditions and capabilities

    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
     则
    0.45
     antibody
    0.44
     endothelial
    0.42
    enda
    0.42
     distillate
    0.42
     Immunohist
    0.42
     family
    0.42
     transcript
    0.41
     hereditary
    0.41
     sacr
    0.41
    POSITIVE LOGITS
     ಸಮಯ
    0.51
    テレ
    0.45
    忙
    0.45
    सु
    0.45
    логов
    0.44
    ಸ್ಕೊ
    0.43
    缺少
    0.43
    Гра
    0.42
    紫色
    0.42
    У
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.