© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13312
    Prev
    Next
    INDEX
    Explanations

    list of items

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

    The neuron is specialized in detecting numeric tokens—especially multi-digit and decimal numbers (e.g., measurements, prices, 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
     códigos
    0.88
    
    0.82
    hound
    0.80
    睺
    0.77
    んじゃない
    0.77
    म
    0.77
    शील
    0.76
    𝗦
    0.76
    බන්ධ
    0.75
    បទ
    0.75
    POSITIVE LOGITS
    tan
    0.84
    sum
    0.78
    sd
    0.78
    sq
    0.73
    tim
    0.73
    sf
    0.71
    sy
    0.71
    lished
    0.70
    sis
    0.70
    sl
    0.70
    Activations Density 0.000%

    No Known Activations