© 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. 61085
    Prev
    Next
    INDEX
    Explanations

    local community and place identifiers

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

    The neuron fires on the word “local,” flagging mentions of locality or local entities.

    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
    guigu
    -1.67
    ༅
    -1.43
    غال
    -1.39
    borsa
    -1.39
    了解更多
    -1.33
    Hozzáférés
    -1.30
     började
    -1.30
    ．．
    -1.28
     Currently
    -1.27
     который
    -1.25
    POSITIVE LOGITS
    3
    1.53
    幔
    1.52
     passione
    1.49
     vicina
    1.45
    [
    1.44
     Enciclopedia
    1.41
    眎
    1.39
    躋
    1.39
     フー
    1.38
    Ligações
    1.38
    Activations Density 0.007%

    No Known Activations