© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14534
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly sensitive to low‐frequency, content‐heavy tokens—that is, unusual or specialized vocabulary.

    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
    ↵
    1.09
        
    1.05
    )).
    0.89
    ().
    0.86
    0.86
    ({
    0.86
         
    0.85
    ()));
    0.85
          
    0.85
    ();
    0.85
    POSITIVE LOGITS
     perishable
    0.91
     concierge
    0.86
     supercar
    0.84
     tirelessly
    0.83
     diligently
    0.83
     tireless
    0.82
     inflexible
    0.82
     multifunctional
    0.82
     intranet
    0.82
     hydropon
    0.81
    Activations Density 0.000%

    No Known Activations