© 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. 22-GEMMASCOPE-RES-131K
    7. 27010
    Prev
    Next
    INDEX
    Explanations

    events, publications, and training

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

    The neuron detects words referring to organized educational or professional events (e.g., lectures, conferences, workshops, classes, seminars).

    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
     details
    -1.06
     依
    -1.02
    つつ
    -0.99
    gebiete
    -0.98
     attributes
    -0.96
    瑣
    -0.96
     względem
    -0.92
     nochmal
    -0.92
    gmail
    -0.90
     characteristics
    -0.89
    POSITIVE LOGITS
     or
    1.29
    Regel
    1.27
    curkan
    1.15
     souvent
    1.14
    brtc
    1.12
     ſur
    1.11
    ḿ
    1.10
    เกี่ยวกับ
    1.06
     about
    1.04
     déchir
    1.04
    Activations Density 0.069%

    No Known Activations