© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13171
    Prev
    Next
    INDEX
    Explanations

    publication/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    스템
    2.08
     오브
    2.08
    墟
    2.04
    蒡
    2.00
    ldigt
    1.99
    ேத்க
    1.98
     바탕
    1.97
    玩意
    1.95
    嶋
    1.93
    뻗
    1.92
    POSITIVE LOGITS
     repayment
    1.77
    Automatic
    1.62
    ようです
    1.60
    Normally
    1.59
    Income
    1.59
    Í
    1.58
     telemetry
    1.54
    Usually
    1.53
    🚚
    1.51
     characteristics
    1.50
    Activations Density 0.001%

    No Known Activations