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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55830
    Prev
    Next
    INDEX
    Explanations

    names of physics departments

    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
    ausch
    -0.78
    ナン
    -0.76
     charmed
    -0.73
    garan
    -0.72
     Destination
    -0.72
    γη
    -0.72
    صور
    -0.72
    ytt
    -0.71
     ngữ
    -0.71
     Babylon
    -0.70
    POSITIVE LOGITS
    moved
    0.71
    も見
    0.69
    +"/
    0.69
    гласно
    0.67
     kommenden
    0.67
     خارجی
    0.66
     préparation
    0.66
    illust
    0.65
     planning
    0.65
     测试
    0.65
    Activations Density 0.024%

    No Known Activations