Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8413
    Prev
    Next
    INDEX
    Explanations

    analysis and evaluation

    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_262k_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
     
    0.38
     around
    0.37
     power
    0.37
     gü
    0.36
     profiter
    0.36
     t
    0.35
    ço
    0.34
      
    0.34
     down
    0.34
     drizzle
    0.34
    POSITIVE LOGITS
     достовер
    0.51
     анализ
    0.51
    分析
    0.48
     विश्लेषण
    0.47
     분석
    0.46
     análise
    0.46
     évaluations
    0.45
    analysis
    0.44
     ANALYSIS
    0.44
    анали
    0.44
    Activations Density 0.000%

    No Known Activations