© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109797
    Prev
    Next
    INDEX
    Explanations

    political figures' names

    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
    Avo
    -0.85
    Ema
    -0.73
    Kni
    -0.73
    Nio
    -0.69
     oreja
    -0.69
    atko
    -0.68
     шум
    -0.68
    pricing
    -0.68
     dyna
    -0.68
     recuperación
    -0.68
    POSITIVE LOGITS
     Ging
    1.16
     Herman
    1.14
     Newt
    1.08
     Ron
    1.06
    Ron
    1.04
    Herman
    1.02
     Romney
    1.01
     HPV
    0.99
     Mitt
    0.95
    RON
    0.89
    Activations Density 0.044%

    No Known Activations