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. 8548
    Prev
    Next
    INDEX
    Explanations

    names containing Republic

    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
    ņi
    -0.78
    дор
    -0.75
     možnost
    -0.74
    namese
    -0.73
     brillantes
    -0.72
     kneel
    -0.72
    oplayer
    -0.71
     
    -0.71
    Jamaica
    -0.71
     conseil
    -0.71
    POSITIVE LOGITS
     rin
    0.65
     always
    0.63
    convite
    0.62
    miyorum
    0.62
     emozioni
    0.62
     Hoh
    0.60
    toDo
    0.60
     estrema
    0.60
    disease
    0.60
    itable
    0.60
    Activations Density 0.058%

    No Known Activations