© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43093
    Prev
    Next
    INDEX
    Explanations

    Mets, Zimmerman, Hedgehog, ExceptionHandler

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    There
    -2.55
    葙
    -2.55
    It
    -2.50
    Sekarang
    -2.28
     tinham
    -2.22
    8
    -2.14
    Tujuan
    -2.09
    Setelah
    -2.09
    Kesimpulan
    -2.09
    5
    -2.08
    POSITIVE LOGITS
     was
    2.80
    as
    2.63
    f
    2.39
    垍
    2.30
    (
    2.28
    洧
    2.19
    リビング
    2.17
     pewno
    2.16
     队
    2.09
    )-
    2.08
    Activations Density 0.002%

    No Known Activations