© 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. 113186
    Prev
    Next
    INDEX
    Explanations

    notifications sending and receiving

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

    the word "Notification" or variations of it (like "notifications", "NOTIFICATION") in technical or programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on mentions of “notification” (and its variants like “notifications,” “notify,” etc.), especially in code or API names.

    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
    You
    -2.39
    x
    -2.39
    i
    -2.28
    of
    -2.17
    2
    -2.14
    I
    -2.13
    Some
    -2.13
    In
    -2.11
    y
    -2.11
    g
    -2.09
    POSITIVE LOGITS
    桕
    2.39
    を選ぶ
    2.33
    を変える
    2.25
    を選
    2.22
    選ぶ
    2.13
    でご
    2.08
    の方は
    2.00
    🛇
    2.00
    
    1.99
    鶿
    1.99
    Activations Density 0.011%

    No Known Activations