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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 279
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and abbreviations

    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_7_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
    -
    1.45
    .
    1.33
    !
    1.25
     and
    1.20
    (
    1.17
    ,
    1.15
    '
    1.15
    ;
    1.11
     that
    1.07
    on
    1.07
    POSITIVE LOGITS
     aşağıdaki
    2.19
     dalších
    2.03
     tiež
    1.97
     prestataire
    1.94
    Issledovatel
    1.94
     sélectionnez
    1.89
     zejména
    1.89
     különböző
    1.87
     diğer
    1.87
    JlcG
    1.86
    Activations Density 2.230%

    No Known Activations