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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75603
    Prev
    Next
    INDEX
    Explanations

    query, labels, columns, shapes

    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
    Their
    -1.54
     их
    -1.30
    Waktu
    -1.20
    Pener
    -1.17
    kter
    -1.17
    ținut
    -1.16
    Lebih
    -1.14
     their
    -1.13
    他们的
    -1.13
     -}
    -1.11
    POSITIVE LOGITS
     from
    1.29
    阑
    1.17
     also
    1.16
     of
    1.15
     in
    1.13
     bahkan
    1.09
     Also
    1.06
     our
    1.06
     tricot
    1.06
     propelled
    1.05
    Activations Density 0.603%

    No Known Activations