© 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-262K
    7. 138987
    Prev
    Next
    INDEX
    Explanations

    describing shapes

    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
    增速
    0.48
    锴
    0.47
    臭
    0.46
    <unused987>
    0.46
    sik
    0.46
    䪱
    0.46
    <unused229>
    0.46
    聩
    0.45
    不对
    0.45
    
    0.45
    POSITIVE LOGITS
    0
    0.71
    4
    0.61
    -
    0.59
     laboratory
    0.53
    1
    0.50
    8
    0.49
     πε
    0.48
    ars
    0.47
     computer
    0.46
     theater
    0.46
    Activations Density 0.000%

    No Known Activations