© 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. 75007
    Prev
    Next
    INDEX
    Explanations

    technical components and roles

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

    The main thing this neuron does is spot technical/mechanical component and equipment nouns.

    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
     have
    -1.53
     what
    -1.45
    5
    -1.44
     llegaron
    -1.37
     haberse
    -1.36
     our
    -1.34
     hingegen
    -1.34
     tuvieron
    -1.33
    𝚊
    -1.29
     only
    -1.28
    POSITIVE LOGITS
    cof
    1.34
     Tô
    1.30
    amples
    1.27
    🤯
    1.26
    edade
    1.25
    😯
    1.24
    😻
    1.20
    😲
    1.20
     him
    1.18
     kHz
    1.18
    Activations Density 1.509%

    No Known Activations