© 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. 130895
    Prev
    Next
    INDEX
    Explanations

    named entities and places

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

    This neuron responds to tokens that are part of capitalized named entities—especially institution, place, or infrastructure names (e.g. IITs, railway stations, express trains, geographic locations).

    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
    nements
    -1.28
    atization
    -1.23
    
    -1.18
    鴴
    -1.18
     ovale
    -1.16
     abonnement
    -1.13
    aires
    -1.13
    uded
    -1.13
    alogical
    -1.12
    ꒪
    -1.11
    POSITIVE LOGITS
    '
    1.25
     will
    1.24
     could
    1.23
     when
    1.21
     under
    1.20
     kid
    1.18
    再来
    1.18
     how
    1.16
     within
    1.16
     after
    1.16
    Activations Density 0.050%

    No Known Activations