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. 7867
    Prev
    Next
    INDEX
    Explanations

    historical people and places

    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
     seventeenth
    -0.80
     telegraph
    -0.78
     dodge
    -0.75
     Arp
    -0.75
    Activités
    -0.73
    DOCTYPE
    -0.73
     train
    -0.73
    孽
    -0.73
     tươi
    -0.71
    ODM
    -0.71
    POSITIVE LOGITS
     Napoleonic
    1.06
     Regency
    0.96
     Отечественной
    0.96
     Rossini
    0.86
    ⠅
    0.78
    contentType
    0.71
     Edinburgh
    0.71
     Fourier
    0.70
    DUMP
    0.70
     Greece
    0.70
    Activations Density 0.118%

    No Known Activations