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. 12
    Prev
    Next
    INDEX
    Explanations

    progressive politics and activism

    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
    voegen
    -0.89
     negroes
    -0.87
     fiyatı
    -0.81
    み
    -0.79
    ụ
    -0.79
     alanı
    -0.78
     Sciento
    -0.78
    Gör
    -0.77
    yectos
    -0.77
    scipy
    -0.76
    POSITIVE LOGITS
     Chomsky
    1.36
     Zinn
    1.00
     Acti
    0.96
    progressive
    0.91
     Occup
    0.91
     progressive
    0.86
     Alter
    0.81
     Manufacturing
    0.80
     anti
    0.79
    arnos
    0.79
    Activations Density 0.109%

    No Known Activations