Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8737
    Prev
    Next
    INDEX
    Explanations

    7 + 7

    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
     againſt
    -0.80
    Моя
    -0.80
    Какие
    -0.79
     Qualquer
    -0.79
    szt
    -0.77
    でございます
    -0.76
    Юлия
    -0.76
    Марина
    -0.75
    ıştı
    -0.75
    nasel
    -0.75
    POSITIVE LOGITS
    vand
    1.09
    che
    1.05
     etc
    1.05
    cip
    0.94
    TInt
    0.92
    λη
    0.90
    ho
    0.88
    lins
    0.88
    fram
    0.86
    alty
    0.85
    Activations Density 0.003%

    No Known Activations