© 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. 10-GEMMASCOPE-RES-131K
    7. 71139
    Prev
    Next
    INDEX
    Explanations

    giveaway promotions

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

    The neuron fires strongly on mentions of “giveaway” (and its nearby context), i.e. it detects references to contests or promotional giveaways.

    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
     \
    -3.53
    </i>
    -3.03
    </b>
    -3.00
    re
    -2.89
    }
    -2.80
     =
    -2.55
    ar
    -2.52
    in
    -2.48
     '
    -2.47
    \
    -2.42
    POSITIVE LOGITS
    铙
    2.38
     花纹
    2.31
    quelles
    2.31
    狴
    2.25
    ༣
    2.25
    
    2.23
     素描
    2.22
     nuages
    2.17
     твоя
    2.16
     zoude
    2.14
    Activations Density 0.003%

    No Known Activations