© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6299
    Prev
    Next
    INDEX
    Explanations

    explaining topics or breakdowns

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is essentially inactive (it does not respond to any tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     Cube
    0.70
     manned
    0.70
     कुंजी
    0.69
     Nig
    0.65
     some
    0.64
     Woch
    0.64
    
    0.64
     summation
    0.64
    
    0.64
     دسمبر
    0.63
    POSITIVE LOGITS
    م
    0.79
    ת
    0.76
    <h3>
    0.75
    <blockquote>
    0.75
    COME
    0.73
    zelfde
    0.70
    м
    0.69
    ಾ
    0.67
    า
    0.67
    म
    0.66
    Activations Density 0.003%

    No Known Activations