© 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. 6646
    Prev
    Next
    INDEX
    Explanations

    list formatting (bullets, asterisks)

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

    The neuron fires on isolated numeric tokens—especially digits denoting times, measurements, prices or other quantitative values.

    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
    InterfaceLine
    0.62
    ᚑ
    0.57
     डिपॉ
    0.54
    MiddleLine
    0.54
     Ausstattung
    0.54
     signalé
    0.53
    <unused84>
    0.52
    َي
    0.52
     जवळ
    0.52
    舺
    0.52
    POSITIVE LOGITS
       
    0.80
      
    0.79
    that
    0.71
     it
    0.71
        
    0.70
         
    0.69
    each
    0.68
     a
    0.66
    https
    0.66
    http
    0.64
    Activations Density 0.000%

    No Known Activations