© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1489
    Prev
    Next
    INDEX
    Explanations

    author first names to last names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    1.00
    0.97
     (
    0.97
    ↵
    0.96
    ,
    0.96
     {
    0.94
     given
    0.90
     using
    0.86
     *
    0.83
       
    0.83
    POSITIVE LOGITS
    chyné
    1.49
     filóso
    1.42
     Nietzsche
    1.36
    iavelli
    1.35
    ੲ
    1.34
    <unused1854>
    1.34
     אטאטורק
    1.33
     romanzo
    1.33
    ômios
    1.33
    arrerol
    1.32
    Activations Density 0.075%

    No Known Activations