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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7430
    Prev
    Next
    INDEX
    Explanations

    5xx HTTP status codes

    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
    Peace
    1.11
     refugee
    1.09
     Kashmir
    1.02
     Kurdistan
    1.00
    柿
    1.00
    Maple
    0.99
    news
    0.98
    Palest
    0.98
    ニュース
    0.98
    News
    0.97
    POSITIVE LOGITS
    殿
    0.91
     Johnson
    0.88
     QM
    0.83
     Pfeiffer
    0.82
    وص
    0.81
    Фор
    0.81
     loo
    0.80
    únior
    0.79
    儕
    0.79
    皇家
    0.78
    Activations Density 0.090%

    No Known Activations