© 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. 3772
    Prev
    Next
    INDEX
    Explanations

    Run as administrator

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

    import and from statements

    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
    spiderX
    0.41
    骶
    0.41
    퐫
    0.41
    новниш
    0.38
     cysts
    0.38
    𝓮
    0.38
    笙
    0.38
     علیہ
    0.37
     mè
    0.37
    讧
    0.37
    POSITIVE LOGITS
    s
    0.44
    zer
    0.41
    le
    0.41
    >);
    0.41
    LE
    0.39
    ‘
    0.39
    2
    0.39
    old
    0.38
    <0x0D>
    0.38
    Cal
    0.38
    Activations Density 0.041%

    No Known Activations