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. 8527
    Prev
    Next
    INDEX
    Explanations

    `dart` `group` `new`

    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
     calib
    -0.78
    itemId
    -0.77
    LING
    -0.73
     psalm
    -0.73
     Dominguez
    -0.72
    Lugar
    -0.71
    itarios
    -0.70
     amanda
    -0.70
     Kaffe
    -0.70
    手順
    -0.70
    POSITIVE LOGITS
     APK
    0.93
     URL
    0.91
    xX
    0.86
     MP
    0.81
     ND
    0.80
     ſtre
    0.79
    IEE
    0.79
    antine
    0.78
     TC
    0.78
     roam
    0.77
    Activations Density 0.090%

    No Known Activations