© 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. 11376
    Prev
    Next
    INDEX
    Explanations

    classic, discarded, outsource, owned, get, mins

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

    The neuron selectively activates on numeric tokens (e.g. years, statistics, page or volume numbers, URLs, counts) in the text.

    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
     lưng
    0.83
     باندې
    0.75
    тим
    0.74
     पण
    0.72
    但
    0.72
    من
    0.71
    但在
    0.70
    équipement
    0.70
    وی
    0.68
    देव
    0.66
    POSITIVE LOGITS
    lever
    0.84
    yesha
    0.83
     düzey
    0.82
     desech
    0.82
    prev
    0.81
    pods
    0.80
    ’:
    0.80
     menciona
    0.79
    levels
    0.79
    jz
    0.79
    Activations Density 0.000%

    No Known Activations