© 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. 41154
    Prev
    Next
    INDEX
    Explanations

    serving and feeding

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

    The neuron fires on verbs that express a supply or service relationship between entities (e.g. “feeds,” “served,” “serves”).

    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
     they
    -1.48
     miele
    -1.34
     sicura
    -1.29
    odus
    -1.26
    essi
    -1.23
    。”
    -1.23
    borgen
    -1.22
    ㆆ
    -1.22
    衕
    -1.22
     hän
    -1.20
    POSITIVE LOGITS
     extraordinaire
    1.38
    不仅
    1.36
    AdvEx
    1.34
     jusque
    1.32
    攷
    1.22
     kutoka
    1.20
     gravit
    1.19
    Ummm
    1.19
     Wird
    1.17
    无论是
    1.17
    Activations Density 0.152%

    No Known Activations