© 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. 59930
    Prev
    Next
    INDEX
    Explanations

    obtener, buscar o recibir información

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

    The neuron detects words meaning “obtain/ fetch/ get” (e.g. Spanish “obtener,” Chinese “查看” or “抓取,” Russian “получение,” etc.).

    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
    i
    -2.44
    釓
    -2.38
    and
    -2.36
     TRANSACTION
    -2.30
    𔘓
    -2.28
    }$
    -2.28
    鋱
    -2.23
     Senin
    -2.20
    also
    -2.17
    孥
    -2.17
    POSITIVE LOGITS
     Their
    2.88
     ‘‘
    2.66
    .’
    2.66
    谖
    2.33
     Главная
    2.31
     Other
    2.22
    aticano
    2.19
     Lots
    2.19
    ໊
    2.17
    . 
    2.16
    Activations Density 0.001%

    No Known Activations