© 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. 15314
    Prev
    Next
    INDEX
    Explanations

    measures and arrangements

    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
     of
    -2.06
     gän
    -1.52
    ortun
    -1.48
     sorgfäl
    -1.47
     vieler
    -1.44
    蟊
    -1.41
    说道
    -1.41
     reduzir
    -1.40
     enlar
    -1.36
    那天
    -1.35
    POSITIVE LOGITS
    凊
    1.80
    Sekarang
    1.70
     arrangements
    1.67
     remedio
    1.64
     egna
    1.63
     innan
    1.52
     omfatt
    1.49
    Jangan
    1.47
     huvud
    1.45
     käns
    1.45
    Activations Density 0.021%

    No Known Activations