© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35965
    Prev
    Next
    INDEX
    Explanations

    locations and places

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

    This neuron selectively activates on proper nouns and other named‐entity tokens (e.g., names of people, places, ships, or unique objects).

    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
     and
    -1.62
     their
    -1.55
    眼下
    -1.34
    /*!
    
    -1.12
     similarly
    -1.12
     each
    -1.11
     requires
    -1.09
    ({},
    -1.08
     मुझे
    -1.06
     劉
    -1.05
    POSITIVE LOGITS
     catalana
    1.33
    ซึ่ง
    1.30
    Garantie
    1.28
     Selama
    1.26
    <bos>
    1.20
     вашу
    1.18
     rêves
    1.16
     Meski
    1.16
     חיצוני
    1.13
    CARACTERÍSTICAS
    1.13
    Activations Density 0.069%

    No Known Activations