© 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. 10-GEMMASCOPE-RES-131K
    7. 1733
    Prev
    Next
    INDEX
    Explanations

    city or street blocks

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

    The main thing this neuron does is detect mentions of city blocks (or distances/locations measured in “block(s)”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to city blocks and block-based locations or distances in urban settings.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "block" or "blocks" used in contexts describing physical city blocks or spatial distances.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    {
    -1.84
     SHOULD
    -1.66
    “)
    -1.59
     tiens
    -1.58
     réinitial
    -1.55
    itarianism
    -1.53
    罨
    -1.50
    んび
    -1.49
     與
    -1.48
    IZACIÓN
    -1.46
    POSITIVE LOGITS
     '
    1.87
     where
    1.73
    '
    1.70
     [
    1.69
    笵
    1.66
    :
    1.61
    ing
    1.59
     «
    1.58
     I
    1.55
    著名
    1.55
    Activations Density 0.010%

    No Known Activations