© 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. 22-GEMMASCOPE-RES-131K
    7. 67745
    Prev
    Next
    INDEX
    Explanations

    street names

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

    The neuron fires on road‐type terms in place names (e.g. “Street,” “Drive,” “Avenue,” “Boulevard”) when they appear as part of an address.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    else
    -1.02
    윤
    -0.91
     Komponist
    -0.87
    所有
    -0.84
    Else
    -0.84
     erläut
    -0.83
    zoe
    -0.83
    like
    -0.83
     из
    -0.82
     ži
    -0.82
    POSITIVE LOGITS
     street
    1.27
    jmniej
    1.27
     Street
    1.23
    genden
    1.16
    estrian
    1.09
    onsored
    1.05
     незавер
    1.05
    ◨
    1.05
    ఈ
    1.05
    icksburg
    1.03
    Activations Density 0.023%

    No Known Activations