© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 1754
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and factorials

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

    The neuron strongly fires on numeric tokens—especially floating‐point or decimal numbers—marking spans that represent precise measurements or statistics.

    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
    模
    0.64
     micrographs
    0.59
    phin
    0.57
     conjugate
    0.57
    ButtonGroup
    0.57
     lesions
    0.55
     filamentous
    0.54
    姉
    0.54
     modality
    0.53
    に移
    0.53
    POSITIVE LOGITS
     }{\
    0.91
    )}{\
    0.81
    })}{\
    0.80
     }}{\
    0.79
    }}{\
    0.75
    )}}{\
    0.75
    ]}{\
    0.73
    }{\
    0.73
    }}}{\
    0.73
    》、《
    0.72
    Activations Density 0.010%

    No Known Activations