© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13967
    Prev
    Next
    INDEX
    Explanations

    identifying objects, potential issues, or questions

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

    The neuron activates on numeric tokens—especially large or decimal numbers representing measurements or quantities.

    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
     but
    0.93
     this
    0.91
    它
    0.86
        
    0.86
     pero
    0.84
     it
    0.83
    这个
    0.81
    0.80
    <0xE3>
    0.77
     name
    0.75
    POSITIVE LOGITS
    potentially
    0.80
     indivíduos
    0.79
     ausreiche
    0.77
     individus
    0.73
     υψη
    0.73
     કોઈપણ
    0.71
     थेट
    0.69
    MPa
    0.69
     sólidos
    0.68
     Cualquier
    0.68
    Activations Density 0.001%

    No Known Activations