© 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. 4797
    Prev
    Next
    INDEX
    Explanations

    by their nature

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

    This neuron specializes in detecting numeric strings—especially numbers containing decimal points or period-delimited identifiers (e.g. DOIs, statistical figures, decimal 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
    i
    1.08
    ed
    0.93
    et
    0.86
    ان
    0.75
    il
    0.73
    oré
    0.73
    ின்றன
    0.72
    optimal
    0.70
     optimal
    0.70
     می‌توان
    0.70
    POSITIVE LOGITS
    𝓹
    0.86
     locaux
    0.85
     škole
    0.80
     clearContext
    0.80
    㠃
    0.80
     надеюсь
    0.79
     avait
    0.79
     molest
    0.79
     thuận
    0.78
    হ্ন
    0.77
    Activations Density 0.000%

    No Known Activations