© 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-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 654
    Prev
    Next
    INDEX
    Explanations

    bibliographic citations

    np_acts-logits-general · gemini-2.5-flash-lite

    currency symbols and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_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
    ח
    0.51
    ام
    0.51
    는
    0.49
    من
    0.48
    ال
    0.46
    نا
    0.46
    は
    0.45
    מ
    0.45
    ک
    0.44
    in
    0.44
    POSITIVE LOGITS
    et
    0.57
    aar
    0.46
    वर्ती
    0.46
    .
    0.45
    elje
    0.45
    etse
    0.44
    krank
    0.43
     tué
    0.42
    a
    0.41
    هام
    0.40
    Activations Density 0.175%

    No Known Activations