© 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. 13896
    Prev
    Next
    INDEX
    Explanations

    options, additional, begins, cancellations

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

    The neuron strongly activates on numeric tokens (especially multi‐digit and decimal numbers) 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
     eg
    0.79
    eed
    0.76
    walker
    0.76
    ፣
    0.75
     digelar
    0.73
    ۾
    0.71
    matching
    0.70
     सां
    0.70
    outcome
    0.68
    ṟ
    0.68
    POSITIVE LOGITS
    ून
    0.91
     recueill
    0.82
     dépour
    0.82
    س
    0.80
    存于互联网档案馆
    0.77
     getIntent
    0.76
     présente
    0.75
    DELTA
    0.75
    ン
    0.75
     quelcon
    0.74
    Activations Density 0.000%

    No Known Activations