© 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. 9484
    Prev
    Next
    INDEX
    Explanations

    rows and columns

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

    The neuron activates on numeric tokens (numbers, including integers and decimals).

    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
    격을
    0.59
    首都
    0.58
     orthon
    0.56
     tele
    0.54
    tele
    0.54
    발
    0.54
    直至
    0.52
     positional
    0.52
    격
    0.52
    mesh
    0.51
    POSITIVE LOGITS
     Rows
    1.06
    Rows
    1.01
     rows
    0.95
     currentRow
    0.93
     row
    0.88
     ROWS
    0.88
     Row
    0.87
    currentRow
    0.83
    getRow
    0.83
    rows
    0.83
    Activations Density 0.006%

    No Known Activations