© 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-16K
    7. 11595
    Prev
    Next
    INDEX
    Explanations

    words or phrases

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

    service connection, AI assistant, price point, Jedi walks

    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_16k_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
    v
    0.92
    z
    0.85
    i
    0.84
    ,
    0.76
    im
    0.73
    k
    0.70
    u
    0.69
    er
    0.68
    í
    0.67
    am
    0.66
    POSITIVE LOGITS
     노
    0.64
     트
    0.61
    preliquidacion
    0.61
     ಅಂಶ
    0.60
     ಅಧಿಕಾರಿ
    0.59
     스테
    0.59
    鰐
    0.58
    television
    0.57
    𝗴
    0.57
     अन्य
    0.57
    Activations Density 2.338%

    No Known Activations