© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116561
    Prev
    Next
    INDEX
    Explanations

    toll booths and facilities

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

    The neuron detects references to electronic toll‐collection systems (e.g., toll booths, automated toll payment, RFID transponders).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moky
    -0.77
    kolen
    -0.74
    ゴム
    -0.71
     tiba
    -0.68
    attn
    -0.68
    罫
    -0.67
     affectionate
    -0.67
    ֙
    -0.67
    قد
    -0.66
    AGEMENT
    -0.66
    POSITIVE LOGITS
     toll
    3.31
     Toll
    2.63
    Toll
    2.48
     tolls
    2.48
    toll
    2.25
     tol
    1.79
     Tol
    1.23
    收费
    1.22
    tol
    1.19
     plazas
    1.19
    Activations Density 0.031%

    No Known Activations