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. 79
    Prev
    Next
    INDEX
    Explanations

    code snippets and questions

    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
    QtWidgets
    -0.77
    dafx
    -0.76
    ņi
    -0.74
    ॲ
    -0.74
     Terrible
    -0.74
    ankin
    -0.72
     terrors
    -0.71
    Tare
    -0.71
     bateaux
    -0.71
    ariah
    -0.70
    POSITIVE LOGITS
     Palm
    0.79
     pouvait
    0.77
    yson
    0.75
    Palm
    0.74
     polí
    0.73
     поверх
    0.72
     princesa
    0.71
    parametric
    0.71
     invitado
    0.71
     EDC
    0.70
    Activations Density 0.012%

    No Known Activations