© 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. 13-GEMMASCOPE-2-RES-65K
    7. 145
    Prev
    Next
    INDEX
    Explanations

    print followed by parenthesis

    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_13_width_65k_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
     re
    0.94
     alter
    0.90
     assign
    0.88
     tend
    0.85
     discre
    0.85
    -
    0.84
     -
    0.82
    alter
    0.78
     furt
    0.77
     it
    0.77
    POSITIVE LOGITS
    chyné
    1.73
    ⵄ
    1.70
     "",
    1.70
     "\"
    1.69
    avkh
    1.69
    <unused1522>
    1.69
    okatokat
    1.68
    <unused1537>
    1.68
    स्ताना
    1.67
     ถนน
    1.67
    Activations Density 0.055%

    No Known Activations