© 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. 61046
    Prev
    Next
    INDEX
    Explanations

    risk of negative outcomes

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

    The main thing this neuron does is find language signaling risk, danger, or threat (e.g., “in danger of,” “risk of,” “threatens to”).

    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
    o
    -1.99
    ностях
    -1.68
     viera
    -1.54
    あとは
    -1.54
    なんとか
    -1.46
     want
    -1.45
    after
    -1.44
    最後は
    -1.43
    しましたが
    -1.40
     umane
    -1.40
    POSITIVE LOGITS
    嫱
    1.73
    鈇
    1.59
     naudoti
    1.49
     så
    1.43
    ЛО
    1.42
    高
    1.42
     keinginan
    1.41
    完全
    1.40
    aikan
    1.38
    ători
    1.37
    Activations Density 0.022%

    No Known Activations