© 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. 36232
    Prev
    Next
    INDEX
    Explanations

    names and actions

    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
     обеспечи
    0.53
     springer
    0.53
    圴
    0.52
    缡
    0.51
    靔
    0.50
    䧏
    0.50
     кван
    0.49
    珢
    0.48
     chercheurs
    0.48
    Workbench
    0.48
    POSITIVE LOGITS
     really
    0.48
     what
    0.46
     want
    0.46
     how
    0.45
     wronged
    0.44
     Actually
    0.43
     पुराने
    0.43
     actually
    0.42
     saying
    0.42
    实话
    0.42
    Activations Density 0.010%

    No Known Activations