© 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. 102045
    Prev
    Next
    INDEX
    Explanations

    skiing and snow sports

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

    The neuron fires on mentions of skiing and ski‐related terms (e.g., “ski,” “skiing,” ski resort/place names).

    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
    ingga
    -1.23
     Michał
    -1.19
    тисти
    -1.13
     that
    -1.12
    estab
    -1.11
    mls
    -1.09
     publicidade
    -1.09
    一辈子
    -1.09
     かわ
    -1.09
    余额
    -1.09
    POSITIVE LOGITS
    </sup>
    1.50
     ski
    1.45
     skis
    1.27
    </b>
    1.26
    </h4>
    1.20
     snowboarding
    1.20
    积
    1.16
     особенно
    1.11
     skiing
    1.09
     woolly
    1.09
    Activations Density 0.110%

    No Known Activations