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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8131
    Prev
    Next
    INDEX
    Explanations

    questions, code, or government titles

    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
     timedelta
    -0.84
    幀
    -0.83
    대
    -0.82
    intptr
    -0.79
    бель
    -0.77
     parity
    -0.76
     徒歩
    -0.76
     node
    -0.76
    gué
    -0.75
    ele
    -0.74
    POSITIVE LOGITS
    Hechos
    0.84
    comida
    0.84
    nude
    0.81
    割合
    0.81
     Heater
    0.81
     Yoko
    0.81
    Textbook
    0.80
    valida
    0.80
    Reminders
    0.79
    quilo
    0.79
    Activations Density 0.000%

    No Known Activations