© 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. 34-GEMMASCOPE-RES-131K
    7. 64707
    Prev
    Next
    INDEX
    Explanations

    code syntax and configuration

    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_34/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
    닌
    -1.04
    >(</
    -1.02
    Ę
    -0.95
    amente
    -0.94
     این
    -0.94
    érrez
    -0.93
     asal
    -0.92
    kunjung
    -0.92
    čka
    -0.91
     kvadrat
    -0.91
    POSITIVE LOGITS
     niektórych
    0.94
     getattr
    0.90
     jego
    0.90
    Mô
    0.86
    他的
    0.84
     cómodo
    0.83
    whose
    0.82
     テーブル
    0.81
     जिसमें
    0.80
     cuja
    0.79
    Activations Density 0.028%

    No Known Activations