© 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. 129922
    Prev
    Next
    INDEX
    Explanations

    movie genres and media types

    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
     splend
    -1.61
     and
    -1.59
    ),
    -1.54
    فاوت
    -1.52
    鋮
    -1.52
     who
    -1.50
     agricultura
    -1.48
     \
    -1.46
    他已经
    -1.46
     comprador
    -1.45
    POSITIVE LOGITS
    _
    1.98
    糴
    1.63
     enfrentan
    1.63
     aseguran
    1.59
     zimowa
    1.57
     accueillir
    1.55
    皷
    1.55
     prouver
    1.54
     maybe
    1.50
    ter
    1.49
    Activations Density 0.031%

    No Known Activations