© 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. 110873
    Prev
    Next
    INDEX
    Explanations

    professions and negative feelings

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

    The neuron fires on content‐bearing words (nouns, verbs, adjectives, etc.) rather than on function words.

    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
    鸨
    -1.41
     حتی
    -1.38
     originali
    -1.38
    元々
    -1.37
     fallu
    -1.33
     ativos
    -1.29
     safest
    -1.28
    もともと
    -1.27
    (ﾟ
    -1.26
    写真は
    -1.24
    POSITIVE LOGITS
     between
    1.88
    providedIn
    1.71
     around
    1.66
    hline
    1.59
     all
    1.58
    hdysval
    1.55
     Uses
    1.48
     about
    1.45
    siębior
    1.42
    MessageOf
    1.41
    Activations Density 0.086%

    No Known Activations