© 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. 8298
    Prev
    Next
    INDEX
    Explanations

    following a period

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

    The neuron is activating on numerical values (especially decimal‐formatted 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
     instituições
    0.87
     нередко
    0.82
     संस्कृति
    0.80
     живут
    0.80
     culturais
    0.78
     teško
    0.77
     indispensables
    0.76
    <unused2141>
    0.76
     combatir
    0.74
     jovens
    0.73
    POSITIVE LOGITS
     Therefore
    0.98
    所以
    0.98
    所以在
    0.95
    Therefore
    0.94
    但是
    0.88
     Hence
    0.86
     However
    0.84
     HOWEVER
    0.84
    ので
    0.82
     BUT
    0.79
    Activations Density 0.650%

    No Known Activations