© 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. 5100
    Prev
    Next
    INDEX
    Explanations

    ki Ra

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

    красный квадрат

    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
    排放
    0.52
    ત્મક
    0.50
    childComplexity
    0.50
    蟎
    0.49
    工地
    0.49
    कार्ट
    0.49
    耳机
    0.48
    ettamente
    0.47
    testAvg
    0.47
    राधिक
    0.47
    POSITIVE LOGITS
     кру
    0.69
     Кру
    0.52
     \
    0.52
    ᅠ
    0.48
     С
    0.48
     круг
    0.46
     окру
    0.46
     Step
    0.46
    коло
    0.46
     так
    0.46
    Activations Density 0.000%

    No Known Activations