© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22464
    Prev
    Next
    INDEX
    Explanations

    C/C++ struct definitions

    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
     identif
    -1.70
    킁
    -1.63
     amazingly
    -1.61
    鹇
    -1.60
     bénéficiaire
    -1.59
    튿
    -1.59
    provide
    -1.59
    creates
    -1.56
    びっくり
    -1.55
    provides
    -1.54
    POSITIVE LOGITS
     with
    2.20
     and
    1.95
     through
    1.88
     as
    1.85
     while
    1.50
     in
    1.47
     during
    1.45
     when
    1.44
     still
    1.44
     prominent
    1.41
    Activations Density 0.010%

    No Known Activations