© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110646
    Prev
    Next
    INDEX
    Explanations

    HTML and code tags

    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
     hunger
    -0.68
    लब्
    -0.68
     Reports
    -0.65
    outube
    -0.60
     difficult
    -0.60
    hunger
    -0.60
    ้ม
    -0.60
    及其
    -0.60
    地図
    -0.59
     SMD
    -0.59
    POSITIVE LOGITS
    CURRENT
    0.85
     красоты
    0.77
    Joint
    0.75
    auf
    0.74
    تش
    0.73
    처
    0.71
    Sophie
    0.70
    ʞ
    0.70
     поднима
    0.70
    Sự
    0.69
    Activations Density 0.065%

    No Known Activations