© 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. 40-GEMMASCOPE-2-RES-262K
    7. 6458
    Prev
    Next
    INDEX
    Explanations

    snake game drawing

    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_40_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
    數據
    0.41
     నాలుగు
    0.40
    脛
    0.40
    issippi
    0.40
     healthful
    0.38
    Generalized
    0.38
     ሚ
    0.38
     मिताली
    0.38
     தலைமை
    0.38
     cdot
    0.37
    POSITIVE LOGITS
     sold
    0.38
    고
    0.35
     जहर
    0.35
     pept
    0.34
    sold
    0.34
     intérieure
    0.33
     Apost
    0.33
     aline
    0.32
    unregister
    0.32
    显
    0.32
    Activations Density 0.001%

    No Known Activations