© 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. 10388
    Prev
    Next
    INDEX
    Explanations

    here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     nguyện
    0.96
    ↖
    0.93
    Ổ
    0.90
     எல்லாம்
    0.89
    함으로써
    0.89
     அனைத்தும்
    0.87
    สะดวก
    0.87
    घ्र
    0.86
    伉
    0.86
    ிலேயே
    0.86
    POSITIVE LOGITS
     times
    1.05
     faces
    1.00
    face
    0.99
     hearts
    0.98
     face
    0.97
     souls
    0.94
    times
    0.93
     underlying
    0.91
    Face
    0.90
    agine
    0.90
    Activations Density 0.061%

    No Known Activations