© 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. 12316
    Prev
    Next
    INDEX
    Explanations

    power dynamics

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

    The neuron is specialized to pick out numeric tokens (especially multi‐digit numbers and 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
    ↵↵
    0.68
    ograma
    0.65
    olg
    0.63
    ämme
    0.63
    europe
    0.63
     pana
    0.63
    enaire
    0.63
    s
    0.61
    startDate
    0.61
    POSAL
    0.61
    POSITIVE LOGITS
    毉
    0.98
     beragam
    0.95
     eigenvectors
    0.89
    愘
    0.88
    偻
    0.86
    ့်
    0.86
     Tính
    0.86
     allerlei
    0.85
    萛
    0.85
     Moskau
    0.85
    Activations Density 0.000%

    No Known Activations