© 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. 3353
    Prev
    Next
    INDEX
    Explanations

    new HIV infections

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

    The neuron detects numeric tokens—especially floating‐point numbers (e.g. measurements, volume or page numbers in citations).

    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
    ри
    1.09
     oceans
    0.80
    霎
    0.77
    এছ
    0.73
     groups
    0.71
     அவ்வ
    0.70
    絖
    0.70
    ми
    0.70
     countries
    0.70
     potions
    0.69
    POSITIVE LOGITS
     INumber
    0.90
    versation
    0.84
    ై
    0.83
    amad
    0.82
     Dimit
    0.80
    ijev
    0.78
     lured
    0.76
    efeuille
    0.75
    로서
    0.75
     wabarakatuh
    0.74
    Activations Density 0.000%

    No Known Activations