© 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. 10344
    Prev
    Next
    INDEX
    Explanations

    recognizing patterns

    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
    per
    2.84
    as
    2.33
    년대
    2.06
     vět
    2.03
    put
    2.00
     mert
    1.99
    ו
    1.95
     put
    1.95
     자
    1.92
    מים
    1.92
    POSITIVE LOGITS
    রুখ
    2.94
    操
    2.85
    substring
    2.59
    lara
    2.56
     Yaad
    2.54
    ውነ
    2.54
    eding
    2.51
    uous
    2.50
    iest
    2.50
     carries
    2.40
    Activations Density 0.519%

    No Known Activations