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. 8467
    Prev
    Next
    INDEX
    Explanations

    words followed by specific 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
     uzyska
    -0.75
     eingerichtet
    -0.74
    www
    -0.74
    kových
    -0.73
     exorbitant
    -0.71
    Rota
    -0.71
    Somer
    -0.71
    骛
    -0.70
    iVar
    -0.70
    リスク
    -0.70
    POSITIVE LOGITS
     ピンク
    0.79
     Figs
    0.76
     Coaches
    0.74
    なのが
    0.72
     ресто
    0.72
     Dip
    0.71
     Lucie
    0.71
    {#
    0.71
     cru
    0.70
     watchdog
    0.70
    Activations Density 0.009%

    No Known Activations