© 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. 28209
    Prev
    Next
    INDEX
    Explanations

    news, events, and debates

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

    This neuron detects mentions of key named entities (places, organisations, people) and associated numeric/location details in news text.

    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
     so
    -1.46
     marvellous
    -1.38
     our
    -1.20
     quite
    -1.19
     shadowy
    -1.14
     heartfelt
    -1.14
     here
    -1.14
     galinha
    -1.05
     (
    -1.05
     That
    -1.04
    POSITIVE LOGITS
    formazione
    1.44
    siębior
    1.28
    іє
    1.27
     possuem
    1.23
    [{\
    1.22
    一旁的
    1.21
     데이터
    1.20
     lmao
    1.20
    ье
    1.20
    anstal
    1.20
    Activations Density 0.016%

    No Known Activations