© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 85
    Prev
    Next
    INDEX
    Explanations

    words followed by specific terms

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

    mathematical acronyms and lists

    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_53_width_65k_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
     T
    0.44
    <0xC2>
    0.44
    0.43
     worth
    0.43
     B
    0.41
    T
    0.41
     Gallery
    0.41
    ,
    0.39
     The
    0.38
     Dinner
    0.38
    POSITIVE LOGITS
    ौसी
    0.44
    蕖
    0.42
     क्रमा
    0.41
    ഹ്ലാ
    0.41
    ヤモンド
    0.41
    孅
    0.40
    క్సి
    0.40
    <unused66>
    0.39
    ાન
    0.39
     دسترس
    0.39
    Activations Density 0.000%

    No Known Activations