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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 158
    Prev
    Next
    INDEX
    Explanations

    choice and decision making

    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
    sied
    -0.80
     geg
    -0.77
     LEG
    -0.77
     Tema
    -0.75
    workflow
    -0.75
    ømme
    -0.75
    IEVE
    -0.75
     requis
    -0.75
    RESS
    -0.74
     sant
    -0.73
    POSITIVE LOGITS
     lottery
    1.08
     gamble
    1.00
    Kah
    0.98
     choice
    0.97
     aversion
    0.96
     option
    0.92
    Behavioral
    0.90
     گزینه
    0.86
     keputusan
    0.86
     regret
    0.85
    Activations Density 0.031%

    No Known Activations