© 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. 13573
    Prev
    Next
    INDEX
    Explanations

    .then(

    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
    anin
    1.65
    niu
    1.58
    ‘
    1.54
     co
    1.50
    ни
    1.50
    W
    1.49
    #
    1.46
     싶
    1.45
    싶
    1.44
     ‘
    1.44
    POSITIVE LOGITS
    elfde
    2.28
    elve
    2.01
    orsa
    1.98
    埔
    1.98
    apeutics
    1.97
    ught
    1.90
    
    1.89
     जानकर
    1.89
     escuelas
    1.88
     रीजनिंग
    1.87
    Activations Density 0.000%

    No Known Activations