© 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. 878
    Prev
    Next
    INDEX
    Explanations

    almost followed by strong adjectives

    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
    ių
    2.04
    ancı
    1.89
    ાડ
    1.84
    പ്പുറ
    1.84
    ു
    1.82
    eson
    1.80
     crayons
    1.79
     spindles
    1.79
    oniazid
    1.74
    ემი
    1.73
    POSITIVE LOGITS
    1.85
    ﹔
    1.73
    ToFile
    1.64
    ท
    1.61
    َم
    1.57
     "<<
    1.57
       
    1.57
        
    1.56
    1.56
    <bos>
    1.56
    Activations Density 0.078%

    No Known Activations