© 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. 22-GEMMASCOPE-RES-131K
    7. 15501
    Prev
    Next
    INDEX
    Explanations

    adding flair, color, or updates

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

    The neuron fires on promotional or descriptive words that indicate adding to or enhancing a product’s appeal (e.g. “add,” “enhance,” “flair,” “fill,” “transform”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ּוֹ
    -1.55
     Anſ
    -1.34
    ִּ
    -1.30
    >−</
    -1.19
    niña
    -1.15
    Locatie
    -1.14
    niños
    -1.14
    ַּ
    -1.13
    FontAwesomeIcon
    -1.13
    Comentários
    -1.13
    POSITIVE LOGITS
     also
    1.26
     your
    1.26
     diverse
    1.22
     different
    1.18
     always
    1.10
    ׇ
    1.10
     instantly
    1.08
    కి
    1.03
     add
    1.02
     Christian
    1.02
    Activations Density 0.023%

    No Known Activations