© 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. 48161
    Prev
    Next
    INDEX
    Explanations

    cross street or border

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

    This neuron responds to words about crossing or traversing boundaries (e.g., “across,” “cross,” “side,” “opposite”).

    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
    ándolo
    -0.76
    hö
    -0.73
     foaming
    -0.73
    стные
    -0.73
     ते
    -0.72
     站
    -0.71
     penguins
    -0.69
     warts
    -0.69
     Stelle
    -0.69
    ссий
    -0.68
    POSITIVE LOGITS
     street
    1.58
     streets
    1.34
    street
    1.16
    STREET
    1.09
     Street
    0.98
    Street
    0.97
     STREET
    0.97
    streets
    0.97
     yield
    0.96
     Streets
    0.90
    Activations Density 0.036%

    No Known Activations