© 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. 3964
    Prev
    Next
    INDEX
    Explanations

    contextual metadata and programming terms

    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
     استخدم
    0.44
    高中
    0.42
    歯
    0.41
     APPLICATION
    0.41
    櫂
    0.41
    ントリー
    0.41
     använder
    0.40
    中使用
    0.39
    Кар
    0.38
     তুলনা
    0.38
    POSITIVE LOGITS
     contexto
    0.51
    context
    0.49
     context
    0.48
     контек
    0.46
     kontek
    0.44
     Context
    0.43
     circunst
    0.42
     _:
    0.40
     società
    0.40
     contexte
    0.40
    Activations Density 0.050%

    No Known Activations