© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11987
    Prev
    Next
    INDEX
    Explanations

    741741 crisis line

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

    The neuron is highly selective for numeric digit tokens—particularly the digit “2.”

    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_31_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
     தல
    0.63
    ِلِّ
    0.59
     combs
    0.59
    唏
    0.59
    保证
    0.58
     บอก
    0.57
    kowicz
    0.57
     Manajemen
    0.57
     garantia
    0.56
    ப்பிட
    0.56
    POSITIVE LOGITS
    rectangular
    0.65
    sizes
    0.58
    any
    0.57
    sentiment
    0.57
    adventure
    0.56
    to
    0.55
     him
    0.55
    rentice
    0.55
    (
    0.55
     Pearson
    0.54
    Activations Density 0.000%

    No Known Activations