© 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. 7-GEMMASCOPE-2-RES-16K
    7. 4112
    Prev
    Next
    INDEX
    Explanations

    cross products, User Defined

    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_7_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
    eo
    2.98
    र
    2.62
    ean
    2.62
    []
    2.59
    esai
    2.56
    e
    2.55
    eh
    2.50
    ToOne
    2.40
    ebe
    2.39
    বিশেষ
    2.37
    POSITIVE LOGITS
    蔔
    3.09
    ים
    2.94
    ਊ
    2.93
    이
    2.82
    𝐳
    2.76
    сти
    2.65
    $(\
    2.63
    \".
    2.60
    .\"
    2.58
     επί
    2.57
    Activations Density 0.105%

    No Known Activations