© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2546
    Prev
    Next
    INDEX
    Explanations

    highway, road, and travel terms

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

    The neuron activates on numeric tokens, i.e. any standalone numbers or numeric 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_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
     walkers
    0.61
     caminando
    0.61
    歩
    0.59
    徒歩
    0.57
     обу
    0.55
     защи
    0.54
     подрост
    0.54
     歩
    0.54
     парт
    0.54
     walker
    0.53
    POSITIVE LOGITS
     highway
    2.48
     freeway
    2.33
     highways
    2.28
     Highway
    2.27
     Interstate
    2.20
    highway
    2.19
     motorway
    2.16
    Highway
    2.09
     interstate
    2.05
     Hwy
    2.03
    Activations Density 0.353%

    No Known Activations