© 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. 92583
    Prev
    Next
    INDEX
    Explanations

    on the street

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

    This neuron responds to phrasing that refers to asking or stopping ordinary people “on the street” (e.g. “a typical man or woman on the street”).

    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
     PEP
    -0.82
    vosť
    -0.80
    羽
    -0.78
     ١
    -0.78
     Giovan
    -0.77
    ٠
    -0.73
    ser
    -0.71
    𝑦
    -0.69
    perms
    -0.69
    ftagPool
    -0.69
    POSITIVE LOGITS
     street
    5.34
     streets
    5.28
    street
    4.00
    streets
    3.84
     Street
    3.48
    Street
    3.44
     STREET
    3.27
     Streets
    3.17
    STREET
    3.13
    Streets
    2.92
    Activations Density 0.048%

    No Known Activations