© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 278
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eight
    0.78
    eight
    0.74
     шести
    0.73
     seven
    0.71
    八
    0.71
     séptimo
    0.71
     ocho
    0.70
     sieben
    0.69
     huit
    0.68
    таж
    0.67
    POSITIVE LOGITS
    3
    1.05
    𝟑
    0.94
    ３
    0.94
    三十
    0.91
    ٣
    0.90
    ৩০
    0.89
    ۳
    0.87
    ३
    0.85
     মঙ্গলবার
    0.84
     ३
    0.84
    Activations Density 1.518%

    No Known Activations