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. 8333
    Prev
    Next
    INDEX
    Explanations

    starts of album titles or phrases

    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
    Literally
    -0.96
     influencers
    -0.96
    葚
    -0.88
    Marry
    -0.85
     domande
    -0.84
     değiş
    -0.84
     isnt
    -0.84
     régal
    -0.82
     için
    -0.81
    占比
    -0.81
    POSITIVE LOGITS
    acu
    0.93
    ographical
    0.92
     idéia
    0.88
    하여
    0.88
     sista
    0.87
     sonriendo
    0.85
    nonumber
    0.84
    →
    0.84
     represent
    0.84
    ([
    0.82
    Activations Density 0.029%

    No Known Activations