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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8486
    Prev
    Next
    INDEX
    Explanations

    numerical ranges with or

    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
    ؐ
    -0.90
    änderung
    -0.88
    páns
    -0.83
    etur
    -0.82
     Мексичка
    -0.82
    ponge
    -0.79
    uruh
    -0.79
     মা
    -0.79
    žné
    -0.78
    cím
    -0.78
    POSITIVE LOGITS
    ral
    0.84
     åren
    0.82
     cerim
    0.80
    MOV
    0.78
    öm
    0.76
    中です
    0.76
     so
    0.75
    rog
    0.75
     suivantes
    0.75
    com
    0.75
    Activations Density 0.017%

    No Known Activations