© 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. 1050
    Prev
    Next
    INDEX
    Explanations

    geometric, complex, varied

    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
     estrada
    0.96
     street
    0.95
     blev
    0.94
     ਰ
    0.93
     राह
    0.92
     reven
    0.92
     実
    0.92
    駅
    0.92
    ட்டம்
    0.89
     रहेगा
    0.89
    POSITIVE LOGITS
     нескольких
    1.64
    หลาย
    1.59
    หลากหลาย
    1.55
     few
    1.50
    few
    1.49
    two
    1.48
     vài
    1.48
     کئی
    1.47
     кілька
    1.46
     кілько
    1.46
    Activations Density 0.589%

    No Known Activations