© 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. 10043
    Prev
    Next
    INDEX
    Explanations

    your pace and interests

    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
    stretched
    0.99
    昙
    0.94
     板
    0.93
     ratione
    0.92
    বের
    0.92
    υσ
    0.91
    闆
    0.90
    勞
    0.89
    πηρε
    0.89
    uris
    0.89
    POSITIVE LOGITS
    mary
    1.07
    marie
    1.05
    amond
    1.03
    MARY
    1.00
    coe
    0.96
    endal
    0.93
    痤
    0.92
    marin
    0.92
    힙
    0.92
    alie
    0.91
    Activations Density 0.065%

    No Known Activations