© 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. 8209
    Prev
    Next
    INDEX
    Explanations

    variable declarations (Dim As Long/Integer/Variant)

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

    The neuron primarily responds to numeric tokens (measurements, counts, or figures).

    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
     ступен
    0.77
     Пу
    0.72
    适
    0.71
    的那
    0.68
    RNN
    0.67
     Fishes
    0.66
     Boż
    0.66
    řeb
    0.64
    说
    0.64
    为止
    0.63
    POSITIVE LOGITS
    ек
    0.86
     microprocessor
    0.86
     مقابلہ
    0.86
    يته
    0.80
     bree
    0.79
    اويه
    0.78
     cryptocurrency
    0.78
    lv
    0.77
    ين
    0.77
    शान
    0.77
    Activations Density 0.000%

    No Known Activations