© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71239
    Prev
    Next
    INDEX
    Explanations

    human services, king lear, owned by

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

    The neuron fires on open-class “content” words (nouns, verbs, adjectives) and stays off for 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
     the
    -1.66
     -
    -1.60
    ↵
    -1.53
     C
    -1.45
    ></
    -1.39
    //
    -1.33
     It
    -1.22
     We
    -1.21
     F
    -1.15
    首歌
    -1.14
    POSITIVE LOGITS
    璣
    1.37
     المعيار
    1.33
    stalgia
    1.27
     Rè
    1.26
     Lettres
    1.23
     artistico
    1.22
    ㅐ
    1.20
    🛇
    1.20
     engraçado
    1.20
    +?
    1.20
    Activations Density 0.022%

    No Known Activations