© 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. 12159
    Prev
    Next
    INDEX
    Explanations

    Manhattan and specific associations

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

    The neuron strongly activates on occurrences of the proper noun “Manhattan,” i.e. mentions of the place name.

    oai_token-act-pair · o4-miniTriggered 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
     jezt
    -2.72
     unſ
    -2.67
     nimmer
    -2.58
     Efek
    -2.58
     pengar
    -2.55
    untuk
    -2.53
    valuable
    -2.47
    嚳
    -2.42
     gewi
    -2.39
     grupper
    -2.39
    POSITIVE LOGITS
     In
    3.47
     bustling
    2.67
     Both
    2.64
    s
    2.63
     After
    2.63
    礎
    2.59
     steadfast
    2.55
    ൎ
    2.52
    眺望
    2.50
     sowohl
    2.47
    Activations Density 0.002%

    No Known Activations