© 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. 12933
    Prev
    Next
    INDEX
    Explanations

    a few options

    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
    앗
    2.53
    ാള
    2.24
    े
    2.08
    kość
    2.02
    힌
    1.97
    ۷
    1.97
    ContentView
    1.96
    ۰
    1.95
    чь
    1.92
    ڑ
    1.90
    POSITIVE LOGITS
    ᅵ
    2.56
     流
    2.50
    ἷ
    2.46
     अफेयर्स
    2.42
    socks
    2.41
    いる
    2.41
    ,\,\
    2.39
    s
    2.37
     PAST
    2.32
     immerse
    2.30
    Activations Density 0.132%

    No Known Activations