© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9605
    Prev
    Next
    INDEX
    Explanations

    after names and titles

    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_22_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
    ooker
    1.08
    comed
    1.05
     வாச
    1.04
    힝
    1.02
    reszt
    1.02
    жере
    1.02
     கல்லூ
    1.02
     муниципалите
    1.01
    yní
    1.01
     Lloyds
    1.00
    POSITIVE LOGITS
     dipping
    0.80
     over
    0.76
     Flexible
    0.73
     Samples
    0.72
     Forms
    0.71
    ّل
    0.69
     flexible
    0.69
     designed
    0.69
     existing
    0.69
     forms
    0.69
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.