© 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. 680
    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_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
     没有
    2.64
     jeopard
    2.46
     brib
    2.40
     攵
    2.39
     predis
    2.36
     demoral
    2.36
    pheromone
    2.34
     fluctuates
    2.33
     craftsmen
    2.32
     inhabiting
    2.29
    POSITIVE LOGITS
    メント
    1.78
    able
    1.72
    ments
    1.72
    op
    1.63
    り
    1.63
    れば
    1.60
    షన్
    1.60
     شدہ
    1.59
    ables
    1.58
    ant
    1.55
    Activations Density 0.436%

    No Known Activations