© 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. 34-GEMMASCOPE-RES-131K
    7. 48734
    Prev
    Next
    INDEX
    Explanations

    workshops and seminars

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

    The neuron fires most strongly on tokens that express quantities or durations (numbers, time spans, counts, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ⅙
    -0.82
     sommige
    -0.78
    simus
    -0.78
     afbeeldingen
    -0.77
     prachtige
    -0.77
     prachtig
    -0.75
    lling
    -0.75
     teka
    -0.74
    Ghz
    -0.73
     فلزی
    -0.72
    POSITIVE LOGITS
     workshops
    5.84
     workshop
    5.38
     Workshops
    4.38
     Workshop
    3.94
    workshop
    3.92
    Workshop
    3.88
    Workshops
    3.80
     WORKSHOP
    3.28
     seminars
    3.19
     talleres
    3.06
    Activations Density 0.070%

    No Known Activations