© 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. 10-GEMMASCOPE-RES-131K
    7. 74048
    Prev
    Next
    INDEX
    Explanations

    special events and accessories

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

    The neuron strongly activates on the adjective “special,” flagging any mention of something being specially offered or highlighted.

    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
    >
    -1.78
            
    -1.67
    .
    -1.57
    )
    -1.56
    "
    -1.50
    \
    -1.48
     successful
    -1.43
    Instead
    -1.42
     gesche
    -1.42
    =
    -1.40
    POSITIVE LOGITS
    égek
    1.90
    roned
    1.84
    豢
    1.74
    </tfoot>
    1.70
    みます
    1.69
    辚
    1.66
     mereka
    1.66
    注意事
    1.63
    LETIN
    1.63
     現貨
    1.59
    Activations Density 0.014%

    No Known Activations