© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10848
    Prev
    Next
    INDEX
    Explanations

    if __name__ == "__main__":

    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_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
    कन्या
    2.54
    बच्चों
    2.18
    ড়াল
    2.15
     下さい
    2.12
    onant
    2.11
    ሙሉ
    2.11
    蒾
    2.07
    CLASSI
    2.06
     اتا
    2.02
    TakeVideo
    2.02
    POSITIVE LOGITS
    â
    1.81
    ็บ
    1.81
     Il
    1.81
     Moh
    1.73
     finais
    1.70
    ca
    1.69
     Die
    1.59
    ej
    1.57
    quiera
    1.56
    NavController
    1.56
    Activations Density 0.884%

    No Known Activations