© 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. 8125
    Prev
    Next
    INDEX
    Explanations

    item identifiers in urls

    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
     الملف
    1.15
     dokumen
    1.08
     monograph
    1.07
    /-/
    1.02
     revisions
    1.00
     memorandum
    1.00
     manuscript
    0.99
     ومش
    0.99
     readme
    0.99
     revision
    0.99
    POSITIVE LOGITS
     বাহাদুর
    1.21
    %{
    1.19
    allows
    1.15
     phủ
    1.15
    బర్
    1.14
     watts
    1.13
     भारती
    1.12
     Ensures
    1.10
     strtoupper
    1.10
    ăș
    1.09
    Activations Density 0.064%

    No Known Activations