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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9540
    Prev
    Next
    INDEX
    Explanations

    a as option marker

    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
    炲
    1.04
    েনারেল
    1.03
     wrześ
    0.99
     целях
    0.99
    炵
    0.98
    тере
    0.97
     потре
    0.97
    統一
    0.96
    镓
    0.95
    환
    0.95
    POSITIVE LOGITS
    bridges
    1.37
    dessus
    0.99
    imagine
    0.97
    bridge
    0.96
    pering
    0.96
    corder
    0.96
    embert
    0.94
     bridges
    0.94
    Hi
    0.89
    ↠
    0.89
    Activations Density 0.015%

    No Known Activations