© 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. 7-GEMMASCOPE-2-RES-16K
    4. 13344
    Prev
    Next
    INDEX
    Explanations

    draw

    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
    s
    1.50
     substantial
    1.37
    self
    1.37
    significant
    1.37
    elf
    1.34
     clopen
    1.34
    additional
    1.32
    substantial
    1.31
    an
    1.31
    es
    1.28
    POSITIVE LOGITS
    
    2.21
     野
    2.12
     東
    2.01
     ZONE
    2.01
    
    2.00
    ┎
    1.99
     GON
    1.98
    
    1.97
    ㎞
    1.96
    
    1.96
    Activations Density 0.004%

    No Known Activations