© 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. 195167
    Prev
    Next
    INDEX
    Explanations

    flight, variants, options, Jan

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

    companies, tech, business

    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
    Chrys
    0.49
    тит
    0.48
    Controlled
    0.46
    творе
    0.46
    Clear
    0.45
    Across
    0.45
    Loy
    0.45
    퀄
    0.43
    Effects
    0.43
     microscopic
    0.42
    POSITIVE LOGITS
    olja
    0.54
    compan
    0.50
    pland
    0.49
    km
    0.49
     dö
    0.47
     antioxid
    0.46
     tem
    0.46
     sonunda
    0.46
     Bayram
    0.45
    posta
    0.45
    Activations Density 0.001%

    No Known Activations