© 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. 10485
    Prev
    Next
    INDEX
    Explanations

    Indonesian, Arabic, Tamil, Amharic, Chinese

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

    The neuron spikes on longer content words that carry derivational or inflectional endings (–ing, –ed, –ant, –s, etc.).

    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
     nuis
    0.73
    ‌ی
    0.71
    sman
    0.70
    öger
    0.68
    
    0.67
     gris
    0.66
     grie
    0.66
    foam
    0.65
    ,.
    0.64
    fruit
    0.64
    POSITIVE LOGITS
    تے
    0.86
    ن
    0.84
    ன
    0.82
    嚯
    0.75
     ሰዎች
    0.75
    拿着
    0.73
    也会
    0.73
    मूलन
    0.73
    想着
    0.72
    嗷
    0.72
    Activations Density 0.000%

    No Known Activations