© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72751
    Prev
    Next
    INDEX
    Explanations

    asks questions or requests comments

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

    The neuron flags words and phrases that form or introduce questions in interview or transcript text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     nostre
    -0.95
     their
    -0.93
     нашем
    -0.90
    🥩
    -0.89
     ledig
    -0.88
     aktuelle
    -0.88
    ludes
    -0.88
     straff
    -0.88
     maux
    -0.87
     perles
    -0.85
    POSITIVE LOGITS
     your
    1.64
     you
    1.27
     вашего
    1.09
    Dichloroprop
    1.03
    你的
    1.02
     שלך
    1.00
     budete
    0.98
    您的
    0.97
     الام
    0.93
    stination
    0.93
    Activations Density 0.006%

    No Known Activations