© 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. 8750
    Prev
    Next
    INDEX
    Explanations

    banks connections, motors running, potential customers

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

    This neuron strongly activates on standalone numeric tokens—especially floating-point numbers used as citations or reference markers.

    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
    ah
    0.75
    j
    0.71
    𝐠
    0.71
    ur
    0.70
     aesthetics
    0.69
    stery
    0.69
     expediency
    0.69
    im
    0.68
    le
    0.68
    ру
    0.67
    POSITIVE LOGITS
    های
    0.86
     فشاں
    0.81
     NÃO
    0.80
    não
    0.79
     نمی
    0.77
    翌
    0.77
    awatir
    0.77
    㓡
    0.76
     respecto
    0.75
     reveló
    0.75
    Activations Density 0.000%

    No Known Activations