© 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. 1267
    Prev
    Next
    INDEX
    Explanations

    descriptive terms and follow-ups

    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
     這
    1.76
     Towers
    1.70
     之
    1.68
     學
    1.67
     อย
    1.67
     sorrows
    1.65
     家具
    1.64
     Workshops
    1.62
     桌
    1.62
     Towns
    1.62
    POSITIVE LOGITS
     configuración
    1.67
     sicuro
    1.66
     molti
    1.61
     insbesondere
    1.61
     sowohl
    1.61
     costitu
    1.60
     frecuente
    1.59
     bestimmt
    1.58
    গুলে
    1.57
     fornire
    1.55
    Activations Density 0.070%

    No Known Activations