© 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. 26795
    Prev
    Next
    INDEX
    Explanations

    dialogue and comedy

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

    The neuron fires on words that describe characters’ emotional reactions or physical expressions (e.g. embarrassed, gaze, rolls eyes, hurt, disgusted).

    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
     respected
    -0.98
     nobis
    -0.91
     jā
    -0.90
     vedo
    -0.89
     granit
    -0.87
     differs
    -0.87
     rilev
    -0.87
    autre
    -0.87
    mulos
    -0.87
    ง่าย
    -0.85
    POSITIVE LOGITS
     comedic
    1.01
     divertidas
    1.01
     hilarious
    1.00
    ​=
    0.97
     cuarentena
    0.96
     aver
    0.94
    ɝ
    0.94
     comedy
    0.94
     budou
    0.92
    generic
    0.91
    Activations Density 0.005%

    No Known Activations