© 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. 7591
    Prev
    Next
    INDEX
    Explanations

    Registry receives

    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
     marah
    2.08
     Banyak
    2.05
     Lihat
    2.04
     Jika
    1.97
     thrive
    1.97
    <unused610>
    1.97
     Meskipun
    1.96
    Jika
    1.96
     น้ํา
    1.95
     Sebuah
    1.93
    POSITIVE LOGITS
     с
    2.07
     за
    1.99
     в
    1.96
     у
    1.92
     не
    1.78
     посредством
    1.77
     вследствие
    1.73
     об
    1.68
     „
    1.68
     функциони
    1.66
    Activations Density 1.043%

    No Known Activations