© 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. 5782
    Prev
    Next
    INDEX
    Explanations

    code generation context

    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
     获取
    0.44
    初始化
    0.43
     manually
    0.42
    ↵
    0.41
     initializing
    0.40
     using
    0.39
     Using
    0.38
     externo
    0.37
     初始化
    0.37
     hoặc
    0.37
    POSITIVE LOGITS
    ๔
    0.36
    츰
    0.32
    ධා
    0.32
    шель
    0.32
    赦
    0.32
    繋がり
    0.31
    ambre
    0.30
    äst
    0.30
    DeathRecord
    0.30
    セラ
    0.30
    Activations Density 0.124%

    No Known Activations