© 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. 67818
    Prev
    Next
    INDEX
    Explanations

    meeting a condition

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

    The neuron detects evaluative adjectives or adverbs that qualify or assess adequacy, quality, or readiness (e.g. “good,” “sufficient,” “valid,” “well,” “ready,” “perfectly”).

    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
     either
    -1.33
     partecipare
    -1.27
    either
    -1.22
     entweder
    -1.18
     to
    -1.16
     portare
    -1.12
     but
    -1.11
    美子
    -1.11
    ícia
    -1.09
    tothe
    -1.09
    POSITIVE LOGITS
    Also
    1.38
     también
    1.27
     rentrée
    1.24
     بشأن
    1.23
    amment
    1.15
    它
    1.14
     değişik
    1.14
     armée
    1.11
    人に
    1.11
     mientras
    1.11
    Activations Density 0.088%

    No Known Activations