© 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. 43788
    Prev
    Next
    INDEX
    Explanations

    rowspan and colspan

    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
     how
    -1.45
     competitivos
    -1.34
     utilizamos
    -1.28
     didn
    -1.27
     what
    -1.27
     esperando
    -1.23
    )
    -1.23
    諍
    -1.23
     transformar
    -1.23
     permitido
    -1.23
    POSITIVE LOGITS
    Kedves
    1.70
    ureux
    1.63
     êtres
    1.47
     jedoch
    1.44
    brtc
    1.38
     shrouded
    1.38
     tuttavia
    1.38
     erweitert
    1.35
     هستند
    1.34
    alers
    1.34
    Activations Density 0.012%

    No Known Activations