© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2522
    Prev
    Next
    INDEX
    Explanations

    equations and codes

    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
    '_{\
    0.44
    [(
    0.38
     %><%=
    0.37
     [(
    0.36
    (((
    0.34
    _{(\
    0.34
     $+\
    0.34
    ([(
    0.34
    *,
    0.33
    再加上
    0.33
    POSITIVE LOGITS
     الدفاع
    0.33
    iót
    0.31
     ඔවුන්
    0.30
     जुगा
    0.30
    瘘
    0.30
    诨
    0.29
     habilidades
    0.29
    ඹ
    0.29
     इंपोर्टेंट
    0.29
    ल्ले
    0.29
    Activations Density 0.056%

    No Known Activations