© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2813
    Prev
    Next
    INDEX
    Explanations

    code principles

    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
    izielle
    0.36
     лого
    0.36
    颔
    0.35
     şehir
    0.35
    閲
    0.34
    క్తి
    0.34
     enkele
    0.34
    园
    0.33
    荚
    0.33
    伍章
    0.33
    POSITIVE LOGITS
     code
    0.41
     fundamental
    0.38
    code
    0.37
     principles
    0.33
    ↵
    0.33
    ্জ
    0.32
     offence
    0.32
    ribut
    0.32
    ↵↵↵↵↵↵↵↵↵
    0.31
     offense
    0.31
    Activations Density 0.000%

    No Known Activations