© 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. 63650
    Prev
    Next
    INDEX
    Explanations

    Regional Head

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

    Recreational Pilot Certificate or Private Pilot Certificate

    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
    Negative Logits
    δο
    0.58
    ന്തപു
    0.45
    ظ
    0.44
    دس
    0.43
    Dealing
    0.43
    ढ़ाई
    0.43
    뽁
    0.43
    зова
    0.43
    дні
    0.42
    支撑
    0.42
    POSITIVE LOGITS
    ersiz
    0.50
     involved
    0.48
     erro
    0.48
     again
    0.47
     unacceptable
    0.47
     congress
    0.46
     ฉ
    0.46
    ீக
    0.46
     exclusively
    0.46
    uela
    0.46
    Activations Density 0.000%

    No Known Activations