© 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. 41093
    Prev
    Next
    INDEX
    Explanations

    provocative, prophetic, derogatory descriptors

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

    The neuron is strongly triggered by the adjective “provocative” (and its closely related forms).

    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
    2
    -2.67
    I
    -2.55
    e
    -2.38
    o
    -2.22
    "
    -2.16
    The
    -2.11
    Según
    -2.09
    3
    -1.92
     برای
    -1.92
    ا
    -1.91
    POSITIVE LOGITS
    ༀ
    2.33
    fortawesome
    2.23
    麈
    2.08
    brates
    2.05
    年
    2.03
    eniem
    2.03
    ﱠ
    2.03
    iocene
    2.02
    
    2.00
    otides
    1.99
    Activations Density 0.005%

    No Known Activations