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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 14413
    Prev
    Next
    INDEX
    Explanations

    around equation security

    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
    phenoxymethyl
    0.51
    ет
    0.48
    т
    0.48
     фактически
    0.47
     была
    0.46
     беше
    0.46
    тров
    0.46
    ت
    0.45
    สุดท้าย
    0.44
    ጷ
    0.44
    POSITIVE LOGITS
     دید
    0.46
     เด่น
    0.46
     completeness
    0.45
     biodiversity
    0.43
     edge
    0.43
     frontage
    0.41
    びに
    0.41
     Compare
    0.41
     is
    0.40
     \%(
    0.40
    Activations Density 0.003%

    No Known Activations