© 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. 10006
    Prev
    Next
    INDEX
    Explanations

    code context

    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
     lessee
    0.93
    Ϩ
    0.92
    Okno
    0.91
     आवासीय
    0.88
     linger
    0.88
     glazing
    0.88
     navigating
    0.88
     stealth
    0.87
     Buyers
    0.87
     Balancing
    0.86
    POSITIVE LOGITS
     town
    0.89
     lengan
    0.89
     пам
    0.87
    Town
    0.87
    एपी
    0.86
     تربیت
    0.83
    峇
    0.82
    તુ
    0.81
    ゥム
    0.81
     Town
    0.81
    Activations Density 0.103%

    No Known Activations