© 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. 1688
    Prev
    Next
    INDEX
    Explanations

    responsibilities or years

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

    .org links

    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
    న్స్‌
    0.23
    मेटिक
    0.20
    枧
    0.20
    ڈن
    0.20
    urte
    0.20
    ర్జాతీయ
    0.20
    砻
    0.20
     محاضره
    0.19
    गाह
    0.19
    വാൻ
    0.19
    POSITIVE LOGITS
     "
    0.20
     can
    0.20
    \)
    0.20
     '
    0.20
     strang
    0.19
    s
    0.19
    icient
    0.19
     tall
    0.18
     ince
    0.18
     o
    0.18
    Activations Density 0.184%

    No Known Activations