© 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. 10198
    Prev
    Next
    INDEX
    Explanations

    promoting positive outcomes

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

    The neuron activates on various inflected forms of the word “promote” (e.g. promote, promotes, promoting, promoted).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    language indicating promotion or enhancement effects (causing or encouraging something to increase or advance).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "promoting" or its variations (promotes, promote, promoted) in scientific and technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     we
    -2.77
     a
    -2.34
     tuvo
    -2.09
    io
    -2.05
     It
    -2.03
     Furcht
    -2.03
    𖣘
    -1.95
    翩
    -1.95
    F
    -1.95
    B
    -1.93
    POSITIVE LOGITS
    腚
    2.14
    м
    2.13
    pendentif
    2.13
    꾹
    2.06
     leaſt
    2.03
     Pantalla
    2.00
    TacToe
    1.96
     ẞ
    1.96
    敺
    1.95
    ？！”
    1.93
    Activations Density 0.013%

    No Known Activations