© 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. 13-GEMMASCOPE-2-RES-65K
    7. 456
    Prev
    Next
    INDEX
    Explanations

    model learns

    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_13_width_65k_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
    เท่า
    0.83
     riguard
    0.81
    B
    0.79
    ซ
    0.77
    Episodes
    0.71
    เนื่อง
    0.70
     B
    0.68
     ด้าน
    0.66
    ภายใน
    0.66
     mentre
    0.66
    POSITIVE LOGITS
     strives
    1.09
     intends
    1.08
     cannot
    1.04
     owes
    1.04
    <unused2223>
    1.03
     proactively
    1.01
    <unused2222>
    1.00
     accepts
    0.99
     continually
    0.98
     reorgan
    0.97
    Activations Density 0.895%

    No Known Activations