© 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. 2422
    Prev
    Next
    INDEX
    Explanations

    calculating or general query

    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
     süreç
    0.50
     sürec
    0.48
     кризи
    0.47
     страте
    0.46
     strategia
    0.44
     négoci
    0.44
    原則
    0.43
    艙
    0.43
     kial
    0.43
     стратегия
    0.42
    POSITIVE LOGITS
    random
    0.64
     Calculator
    0.63
     calculator
    0.61
     Emoji
    0.61
    请输入
    0.61
     usefulness
    0.60
     random
    0.59
     palindrome
    0.59
     Minecraft
    0.57
     meaningless
    0.57
    Activations Density 1.069%

    No Known Activations