© 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. 3999
    Prev
    Next
    INDEX
    Explanations

    superlatives and rankings

    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
    この記事
    1.81
     Ü
    1.72
     항목
    1.70
    áš
    1.60
     작성
    1.58
    andex
    1.58
     eyep
    1.55
     생각
    1.54
     Ä
    1.52
     SK
    1.51
    POSITIVE LOGITS
    ৬
    2.37
    ৭
    1.99
    quinazoline
    1.97
     billionaires
    1.93
     giants
    1.92
    ৩
    1.90
    ৫
    1.90
    rimiento
    1.88
    ১
    1.88
    льно
    1.87
    Activations Density 0.094%

    No Known Activations