© 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. 10-GEMMASCOPE-RES-131K
    7. 8528
    Prev
    Next
    INDEX
    Explanations

    this time or point

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

    The neuron is tuned to detect instances of the demonstrative “this.”

    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
     teknologi
    -1.98
     jajaja
    -1.95
     laki
    -1.91
    屣
    -1.90
     CALIFORN
    -1.88
    皤
    -1.87
     optik
    -1.83
     贺
    -1.78
     خلال
    -1.77
     studenten
    -1.77
    POSITIVE LOGITS
     least
    2.72
    </h4>
    2.67
    </u>
    2.45
     own
    2.25
    uffff
    2.08
    大部分
    1.97
    al
    1.96
     любой
    1.95
     nawet
    1.92
    rangea
    1.92
    Activations Density 0.012%

    No Known Activations