© 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. 58843
    Prev
    Next
    INDEX
    Explanations

    event handler parameters

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

    The neuron activates on identifiers containing the substring “send” (e.g. send, sender, msgSend, author).

    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
     we
    -1.82
     certaines
    -1.62
     první
    -1.60
     you
    -1.58
     reúne
    -1.53
     its
    -1.53
    她就
    -1.52
     the
    -1.52
     ppl
    -1.48
     入っ
    -1.47
    POSITIVE LOGITS
    這個
    1.74
     saveiro
    1.66
    Дом
    1.63
    倧
    1.63
    鱘
    1.61
    .
    1.57
    mäh
    1.55
    ครื่อง
    1.55
    誹
    1.55
    5
    1.54
    Activations Density 0.000%

    No Known Activations