© 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. 86
    Prev
    Next
    INDEX
    Explanations

    very quiet

    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
    <0xC2>
    1.11
    ..."
    1.07
      
    1.05
     [...]
    1.00
     "...
    0.96
     (...)
    0.96
    ...(
    0.94
    [...]
    0.94
     ..."
    0.90
    <eos>
    0.90
    POSITIVE LOGITS
     youll
    0.98
     youre
    0.92
     theyre
    0.91
     buddh
    0.78
     didnt
    0.78
     doesnt
    0.78
     wasnt
    0.78
     france
    0.77
     canadian
    0.76
     jesus
    0.75
    Activations Density 1.430%

    No Known Activations