© 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. 9036
    Prev
    Next
    INDEX
    Explanations

    fractions and quantities in recipes

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

    The neuron strongly activates on whitespace tokens (especially blank‐line or paragraph breaks).

    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
     billion
    0.67
    :
    0.67
     dina
    0.65
     d
    0.64
     COVID
    0.64
     DIN
    0.64
     disrupt
    0.63
     savvy
    0.63
     provisioning
    0.61
     din
    0.59
    POSITIVE LOGITS
     TestAvg
    0.79
    Ⲧ
    0.73
    setRoi
    0.71
    獪
    0.70
     জানিতে
    0.69
     Searching
    0.67
     Utilize
    0.66
     Compose
    0.66
    卩
    0.66
    塡
    0.64
    Activations Density 0.438%

    No Known Activations