© 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. 8149
    Prev
    Next
    INDEX
    Explanations

    San Diego

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

    final answer in a box

    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
    denominator
    0.42
     })
    0.39
     quotient
    0.39
    quorum
    0.38
    recur
    0.36
    Watched
    0.35
     quorum
    0.35
     ඔ
    0.35
    ус
    0.34
     ê
    0.34
    POSITIVE LOGITS
     Rout
    0.41
     ドライバー
    0.40
     जिम्मे
    0.40
    स्यों
    0.40
     παρέ
    0.40
     classrooms
    0.40
     begon
    0.40
     виправи
    0.39
     территории
    0.39
    leadsto
    0.39
    Activations Density 0.000%

    No Known Activations