© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2782
    Prev
    Next
    INDEX
    Explanations

    concerns and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    ">-->
    0.80
    Forgot
    0.77
    "=>
    0.76
     Forgot
    0.70
     "&
    0.69
    last
    0.68
    IGet
    0.68
    LAST
    0.68
                           
    0.67
    {&
    0.66
    POSITIVE LOGITS
    oviruses
    0.78
    Abbreviations
    0.75
     Nomenclature
    0.74
    Fig
    0.72
     Abbreviations
    0.71
     databases
    0.68
     subsection
    0.68
    Subsection
    0.68
    önen
    0.67
    Figs
    0.67
    Activations Density 0.071%

    No Known Activations