© 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. 47526
    Prev
    Next
    INDEX
    Explanations

    expertise and knowledge

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

    The neuron fires on high-value business and technical jargon nouns denoting specialized skills, capabilities, or assets (e.g. “IP,” “competences,” “expertise,” “technologies,” “innovation”).

    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
     affirmé
    -1.40
     intéressante
    -1.38
     sentía
    -1.37
    Detta
    -1.34
    کاربرد
    -1.33
     version
    -1.32
    StandardCharsets
    -1.32
     bArr
    -1.30
    rozum
    -1.30
     fragte
    -1.30
    POSITIVE LOGITS
     debat
    1.36
     igno
    1.35
     abu
    1.34
    urina
    1.32
     dispu
    1.30
     enig
    1.28
     formid
    1.28
     aloe
    1.27
     acci
    1.22
     incompar
    1.21
    Activations Density 0.108%

    No Known Activations