© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 153463
    Prev
    Next
    INDEX
    Explanations

    geographic and administrative divisions

    np_acts-logits-general · gemini-2.5-flash-lite

    capital of kazakhstan or first president

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.66
    t
    0.63
     I
    0.58
    /
    0.55
    ↵↵
    0.53
     favorites
    0.52
     Ready
    0.52
     Err
    0.51
     Str
    0.49
     findings
    0.49
    POSITIVE LOGITS
     نړۍ
    0.55
     мире
    0.55
     உலகின்
    0.55
    ického
    0.55
     архі
    0.54
     દુ
    0.54
    美しい
    0.53
     மேம்ப
    0.53
     войска
    0.53
    
    0.53
    Activations Density 0.001%

    No Known Activations