© 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. 85097
    Prev
    Next
    INDEX
    Explanations

    imperatives and outcomes

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

    The neuron fires on marketing call-to-action phrasing—imperative or exhortative words and short commands urging the reader to do something (e.g. “take…out,” “let us help,” “don’t wait,” “call today”).

    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
    -...
    -1.46
    hever
    -1.42
    peka
    -1.35
    sted
    -1.34
    enough
    -1.34
    someone
    -1.34
    wouldn
    -1.33
    pography
    -1.32
     kasi
    -1.32
    aning
    -1.31
    POSITIVE LOGITS
     your
    1.74
     by
    1.67
    !
    1.58
     this
    1.30
     yourself
    1.28
     has
    1.25
     with
    1.21
     verbindet
    1.20
     без
    1.19
    !!
    1.18
    Activations Density 0.130%

    No Known Activations