© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 904
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
     Basel
    0.97
    Basel
    0.95
     Kenney
    0.94
    Skippable
    0.93
    Brooks
    0.92
     Brooks
    0.92
     Biên
    0.92
    俭
    0.91
    ဖြ
    0.91
    GDP
    0.91
    POSITIVE LOGITS
     magick
    2.85
     magic
    2.67
     magical
    2.63
     witchcraft
    2.58
     mystical
    2.52
     paranormal
    2.50
     Magical
    2.40
     magia
    2.40
     Magic
    2.39
     psychic
    2.37
    Activations Density 2.796%

    No Known Activations