© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6342
    Prev
    Next
    INDEX
    Explanations

    kilometers and miles

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

    The neuron fires on individual numeric digits (numbers) in measurements—i.e. it spots numeric tokens in unit‐conversion sequences.

    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
    onics
    0.83
    te
    0.80
    tw
    0.72
    th
    0.71
    א
    0.69
    dea
    0.67
    ,
    0.67
    egger
    0.66
    tr
    0.64
    se
    0.64
    POSITIVE LOGITS
     magnétique
    0.93
     enseign
    0.89
    చే
    0.88
     ϕ
    0.87
     XPath
    0.82
     remporte
    0.81
    𝐠
    0.81
     étudi
    0.81
    ≣
    0.80
    鹿児
    0.80
    Activations Density 0.008%

    No Known Activations