© 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. 16-GEMMASCOPE-2-RES-65K
    7. 328
    Prev
    Next
    INDEX
    Explanations

    N/A

    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_16_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
     onPress
    0.45
    基本的に
    0.45
    こだわ
    0.44
    forEach
    0.43
    彠
    0.43
     dhinak
    0.43
     выполнение
    0.42
     basePath
    0.41
     ચૂક
    0.40
    핞
    0.40
    POSITIVE LOGITS
     t
    0.57
    ب
    0.57
    ס
    0.55
    ina
    0.54
    u
    0.54
    á
    0.54
    م
    0.52
     in
    0.50
     e
    0.49
    \
    0.49
    Activations Density 0.258%

    No Known Activations