© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 16896
    Prev
    Next
    INDEX
    Explanations

    duration in hours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     syllables
    0.48
     ileti
    0.47
    $).
    0.47
     வசன
    0.45
     سریع
    0.45
    読み
    0.44
     kısa
    0.44
    
    0.44
    $.)
    0.43
     স্বাগত
    0.43
    POSITIVE LOGITS
     hours
    1.34
     Hours
    1.15
     hour
    1.14
    Hours
    1.09
    hours
    1.06
     horas
    1.02
     HOURS
    1.00
     ساعات
    0.99
     Stunden
    0.92
    小时
    0.92
    Activations Density 0.123%

    No Known Activations