© 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. 34-GEMMASCOPE-RES-131K
    7. 93810
    Prev
    Next
    INDEX
    Explanations

    dynamic or variable sizing

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

    The neuron detects verbs and phrases expressing the asker’s need or request (e.g. “need to,” “want to,” “would like,” “can”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    getSingle
    -0.86
     monastic
    -0.82
    퐼
    -0.81
     comparação
    -0.80
    persian
    -0.77
    ㍑
    -0.76
    unsupported
    -0.75
    開發
    -0.75
    Sve
    -0.73
    ルトン
    -0.73
    POSITIVE LOGITS
     dynamic
    3.31
     dynamically
    3.20
    dynamic
    3.06
     adaptive
    3.05
     variable
    2.94
    Dynamic
    2.91
     Dynamic
    2.73
    动态
    2.66
    DYNAMIC
    2.63
    adaptive
    2.56
    Activations Density 0.254%

    No Known Activations