© 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. 800
    Prev
    Next
    INDEX
    Explanations

    non-commercial license

    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
    ia
    1.91
    队的
    1.78
    watched
    1.57
    ๖
    1.56
    <start_of_image>
    1.53
    Opened
    1.50
    Boys
    1.48
    orm
    1.48
    एक
    1.48
    boys
    1.47
    POSITIVE LOGITS
     권
    1.84
     dành
    1.77
     Ausnahme
    1.72
     wyją
    1.69
     동
    1.68
     있으
    1.67
     없음
    1.66
     selain
    1.63
     여름
    1.61
    ன்மைய
    1.60
    Activations Density 0.035%

    No Known Activations