© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 65
    Prev
    Next
    INDEX
    Explanations

    knowledge websites and news sources

    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
     j
    0.52
     neither
    0.52
      
    0.46
     (
    0.46
    <0x0D>
    0.45
     dur
    0.45
     ;
    0.44
     c
    0.43
       
    0.43
     const
    0.41
    POSITIVE LOGITS
     Magazine
    0.98
    Magazine
    0.95
     Matters
    0.87
    Insider
    0.86
    News
    0.85
    Media
    0.84
    Cafe
    0.83
     Insider
    0.82
    Mama
    0.82
    Italia
    0.81
    Activations Density 1.763%

    No Known Activations