© 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. 165182
    Prev
    Next
    INDEX
    Explanations

    as well

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

    diabetic university

    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
     Qué
    0.51
     Örneğin
    0.49
     Đáp
    0.49
     অস্ত্রের
    0.48
     jaunes
    0.46
     bạc
    0.46
     円
    0.45
     चौराहे
    0.45
     ㅛ
    0.45
     bac
    0.44
    POSITIVE LOGITS
    注目
    0.50
    isely
    0.47
    糖尿病
    0.44
    ENCIAS
    0.43
    ;',
    0.42
    ੱਸ
    0.42
    idev
    0.41
    立
    0.41
    тя
    0.41
     hematopoietic
    0.41
    Activations Density 0.000%

    No Known Activations