Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7755
    Prev
    Next
    INDEX
    Explanations

    founder or king titles

    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
    nové
    -0.76
     Michelin
    -0.73
     Europas
    -0.73
     استاد
    -0.72
    metria
    -0.71
    Jes
    -0.71
    ሜ
    -0.70
    mø
    -0.70
    真理
    -0.70
    Kom
    -0.70
    POSITIVE LOGITS
     founder
    1.43
     founding
    1.23
     founders
    1.19
    founder
    1.07
     legend
    1.02
     Founder
    0.99
     legendary
    0.98
     леген
    0.98
     founded
    0.95
    电压
    0.93
    Activations Density 0.049%

    No Known Activations