© 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. 74644
    Prev
    Next
    INDEX
    Explanations

    plotting and visualization libraries

    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
     könnten
    -1.83
    Koordinaten
    -1.61
    out
    -1.57
    In
    -1.55
    其他
    -1.55
     gemeinsamen
    -1.53
    .’
    -1.52
    No
    -1.48
     станет
    -1.47
    .’”
    -1.45
    POSITIVE LOGITS
    tığı
    1.55
    ஂ
    1.54
     mães
    1.54
     vengan
    1.53
    liwości
    1.51
    赌
    1.48
    べし
    1.45
    ſſel
    1.45
    ėte
    1.43
     připo
    1.41
    Activations Density 0.007%

    No Known Activations