© 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. 703
    Prev
    Next
    INDEX
    Explanations

    glad i did

    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
    ">⁢</
    1.39
    Ⴖ
    1.38
    
    1.37
    𐰑
    1.36
    녃
    1.36
    퍁
    1.35
    
    1.35
    ன்ஹீ
    1.33
    Abasis
    1.33
    Ꮞ
    1.32
    POSITIVE LOGITS
     (
    0.82
    (
    0.79
     more
    0.79
     from
    0.77
     faster
    0.72
     bigger
    0.68
     to
    0.68
     "
    0.68
     people
    0.67
     for
    0.66
    Activations Density 0.000%

    No Known Activations