© 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. 15443
    Prev
    Next
    INDEX
    Explanations

    emails, newsletters, marketing messages

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

    The neuron detects proper names, product or service names, and marketing-style feature terms.

    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
     别墅
    -1.36
    wird
    -1.27
     castelo
    -1.26
     skolen
    -1.26
     other
    -1.26
    keine
    -1.25
     kapsul
    -1.24
    ⁇
    -1.23
    Válasz
    -1.23
    varios
    -1.23
    POSITIVE LOGITS
     your
    2.64
     you
    2.13
    }$,
    1.27
     You
    1.23
     
    1.21
     marketing
    1.17
     sent
    1.13
     text
    1.13
     setup
    1.11
    ↵↵↵
    1.10
    Activations Density 0.033%

    No Known Activations