© 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. 2706
    Prev
    Next
    INDEX
    Explanations

    Q, X, q, Rx

    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
     curved
    1.71
     bitter
    1.66
     valve
    1.61
     adventurous
    1.61
     mischievous
    1.58
     recognized
    1.58
     cautious
    1.58
     `;
    1.56
     rhythmic
    1.56
     ladder
    1.55
    POSITIVE LOGITS
     возможностей
    1.78
     بتاع
    1.73
    amentos
    1.71
    كبر
    1.65
    ศัก
    1.64
     algum
    1.64
     tohoto
    1.64
     сосре
    1.63
    AMENTO
    1.62
    شوف
    1.60
    Activations Density 0.006%

    No Known Activations