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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12031
    Prev
    Next
    INDEX
    Explanations

    that which followed by verb

    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_22/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
     it
    -1.49
     there
    -1.27
     böyle
    -1.10
     then
    -1.09
    愎
    -1.05
     чтобы
    -1.04
     habido
    -1.00
     later
    -0.99
     happen
    -0.98
    ousing
    -0.96
    POSITIVE LOGITS
     XIAOMI
    1.01
     Pixels
    1.00
     Adieu
    0.98
     Arabes
    0.97
     Solicit
    0.97
     Menus
    0.95
     tage
    0.95
     silhouettes
    0.92
     TUS
    0.92
     isim
    0.91
    Activations Density 0.056%

    No Known Activations