© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13779
    Prev
    Next
    INDEX
    Explanations

    JSON structure and code tokens

    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_7_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
    ships
    1.25
    peripheral
    1.20
     differing
    1.16
    städ
    1.16
    gtrsim
    1.16
     diverse
    1.15
    diverse
    1.13
    ာ
    1.13
     opulent
    1.13
    ఖ
    1.12
    POSITIVE LOGITS
     viết
    1.71
     yarı
    1.67
     piş
    1.54
     Verme
    1.54
    CharacterSet
    1.52
     ede
    1.50
     béné
    1.49
     S
    1.48
     Lucille
    1.48
     colocar
    1.48
    Activations Density 0.002%

    No Known Activations