© 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. 22-GEMMASCOPE-RES-131K
    7. 68001
    Prev
    Next
    INDEX
    Explanations

    available below or through

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

    The neuron fires strongly on call-to-action and promotional cues—imperative or “click here / learn more / call us” style phrases used in ads or listings.

    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
     flamengo
    -1.27
     péro
    -1.17
     pulsa
    -1.09
     vana
    -1.09
     pican
    -1.08
    bory
    -1.08
    攷
    -1.08
     bunda
    -1.06
     tava
    -1.06
     vinil
    -1.05
    POSITIVE LOGITS
     if
    1.48
    if
    1.21
     below
    1.07
     contact
    1.05
     details
    1.02
     available
    1.01
     attached
    0.99
     clicking
    0.97
     directly
    0.96
     related
    0.95
    Activations Density 0.008%

    No Known Activations