© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13204
    Prev
    Next
    INDEX
    Explanations

    related to protests

    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
    dır
    3.02
    jacking
    2.48
    tte
    2.41
    گرام
    2.35
    €
    2.33
    ﮢ
    2.32
     latch
    2.30
    睺
    2.30
    wiście
    2.29
    йович
    2.28
    POSITIVE LOGITS
    ia
    2.60
    ান
    2.52
    ിച്ചി
    2.47
    ن
    2.39
    с
    2.37
    فاض
    2.29
    ेलर
    2.24
    inental
    2.20
    ଭ
    2.18
    िनय
    2.18
    Activations Density 0.017%

    No Known Activations