© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85611
    Prev
    Next
    INDEX
    Explanations

    electronic devices and systems

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

    The neuron fires strongly on mentions of physical devices or equipment (e.g. appliances, cameras, motors, sensors, vehicles).

    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
     コ
    -1.18
     necesitamos
    -1.17
     necesitas
    -1.14
     quisiera
    -1.13
     irres
    -1.13
    沿い
    -1.13
    glTex
    -1.11
    怎么回事
    -1.10
    abstractmethod
    -1.07
    şiv
    -1.05
    POSITIVE LOGITS
    versace
    1.20
    berserk
    1.17
    backpack
    1.09
     Америка
    1.08
    estens
    1.07
    underwater
    1.06
    patio
    1.04
    😙
    1.03
     same
    1.03
    ？』
    1.02
    Activations Density 0.309%

    No Known Activations