© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35308
    Prev
    Next
    INDEX
    Explanations

    lead ore processing

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

    This neuron flags promotional or sales-style language—words you’d see in tips, calls to action, product pitches, and expressions of thanks in marketing or review copy.

    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
    IVENESS
    -1.14
     samti
    -1.05
    unters
    -1.05
    İL
    -1.04
     vilja
    -1.02
    一定的
    -1.02
     skog
    -1.01
     natten
    -1.01
     hvid
    -1.00
    ꯭
    -1.00
    POSITIVE LOGITS
    </h3>
    1.00
    <blockquote>
    0.94
    ,
    0.91
     gelegt
    0.90
     you
    0.90
     Kontexten
    0.89
    tinyurl
    0.89
    spół
    0.86
     erfü
    0.85
     noastre
    0.85
    Activations Density 0.004%

    No Known Activations