© 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. 62
    Prev
    Next
    INDEX
    Explanations

    street names

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

    The neuron detects occurrences of street‐style addresses, especially the token “Avenue” (and its associated proper names or numbers).

    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
    扨
    -2.73
     può
    -2.53
    鼱
    -2.52
    2
    -2.45
    1
    -2.42
     merav
    -2.38
    麁
    -2.38
    ﱠ
    -2.36
     sufficiente
    -2.34
    힉
    -2.34
    POSITIVE LOGITS
     garner
    2.56
    ↵
    2.52
     longstanding
    2.47
     burgeoning
    2.42
     multifaceted
    2.27
     unrelenting
    2.25
    蕺
    2.23
     exquisitely
    2.22
     здесь
    2.19
     unparalleled
    2.19
    Activations Density 0.014%

    No Known Activations