© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11039
    Prev
    Next
    INDEX
    Explanations

    dynamic programming, sentence subject

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

    The neuron is specialized to detect numerical tokens (i.e. standalone digits or multi‐digit numerals).

    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
    asena
    0.88
     świata
    0.84
     başlad
    0.83
    거나
    0.82
    ៩
    0.82
    setBadge
    0.80
     sobretudo
    0.80
    querysearch
    0.80
    oshape
    0.78
    سمبر
    0.78
    POSITIVE LOGITS
     Regency
    0.79
     Statements
    0.77
     Monuments
    0.77
     ounce
    0.76
     -
    0.74
     unquestion
    0.73
     clauses
    0.73
    -
    0.72
    A
    0.72
    '
    0.72
    Activations Density 2.763%

    No Known Activations