© 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. 2432
    Prev
    Next
    INDEX
    Explanations

    courage and URLs

    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
     이거
    1.35
     pistola
    1.35
     रिटायर
    1.29
     사진
    1.28
    이기
    1.27
     dört
    1.27
     이런
    1.27
    탭
    1.27
    こんな
    1.27
     작은
    1.27
    POSITIVE LOGITS
     implicitly
    1.11
     occurring
    1.05
     finding
    1.04
     manifested
    0.99
     culminated
    0.97
     invariably
    0.96
     leading
    0.95
     intrinsic
    0.95
     enabling
    0.93
     constructively
    0.93
    Activations Density 0.571%

    No Known Activations