© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14792
    Prev
    Next
    INDEX
    Explanations

    in or after

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

    The neuron fires on numeric tokens or symbols—i.e. it’s detecting numbers, percentages, and other numeric expressions 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
    ower
    0.72
    いた
    0.71
     B
    0.70
     вызвать
    0.66
    allow
    0.65
    asty
    0.64
     D
    0.63
    يهم
    0.63
    upp
    0.62
    att
    0.62
    POSITIVE LOGITS
    जैसा
    0.95
    ሖ
    0.83
     như
    0.78
    รู้สึก
    0.78
    
    0.78
     tapi
    0.77
     campeón
    0.77
     cœur
    0.76
     lateribus
    0.76
    producto
    0.75
    Activations Density 0.000%

    No Known Activations