© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44118
    Prev
    Next
    INDEX
    Explanations

    specific entities or places

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

    The neuron detects mentions of specific named entities—formal institutions, organizations, technical objects, or legal documents.

    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
     собрать
    -1.72
     приготовить
    -1.37
    extré
    -1.27
    谁能
    -1.27
    为啥
    -1.25
    peinture
    -1.24
     воспользоваться
    -1.23
    télé
    -1.22
     Ausführungen
    -1.21
     Hvad
    -1.16
    POSITIVE LOGITS
     that
    1.21
     (
    1.19
    約
    1.18
     все
    1.09
     etc
    1.07
    えもん
    1.05
     your
    1.04
     -
    1.03
     sekä
    1.02
     diarias
    1.02
    Activations Density 0.433%

    No Known Activations