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. 8593
    Prev
    Next
    INDEX
    Explanations

    test method declarations

    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
     (!__
    -0.99
    ByDate
    -0.89
     wählen
    -0.82
    真正的
    -0.80
     chosen
    -0.79
    eterminate
    -0.79
    atán
    -0.79
    新增
    -0.79
     slutet
    -0.78
    ὄ
    -0.77
    POSITIVE LOGITS
     (
    1.13
     void
    1.05
    (
    1.01
    void
    0.96
    限り
    0.94
     parati
    0.85
     Henne
    0.83
    hra
    0.83
     jot
    0.82
    expected
    0.82
    Activations Density 0.001%

    No Known Activations