© 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. 70685
    Prev
    Next
    INDEX
    Explanations

    academic references and citations

    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
    tedy
    -1.60
     dificuldade
    -1.48
    さてさて
    -1.44
    為に
    -1.43
     armazenamento
    -1.43
    entrevista
    -1.41
    Tienda
    -1.38
    dijual
    -1.38
    Interes
    -1.37
    chemia
    -1.35
    POSITIVE LOGITS
     will
    2.02
     and
    1.85
     "
    1.80
     включает
    1.43
     должен
    1.38
    fourths
    1.37
    所
    1.35
    所有
    1.33
    ViewChild
    1.33
     GlobalKey
    1.32
    Activations Density 0.010%

    No Known Activations