© 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. 13949
    Prev
    Next
    INDEX
    Explanations

    broadcast and multicast

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

    The neuron fires on words and fragments related to “broadcast” or “casting” (e.g. broadcast, broadcasting, casted).

    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
    他の
    -1.81
    別の
    -1.73
    埽
    -1.65
     zakon
    -1.64
    を選択します
    -1.63
     така
    -1.61
    倩
    -1.61
     vacía
    -1.60
     одной
    -1.59
    -1.59
    POSITIVE LOGITS
    broadcast
    1.94
    umpad
    1.83
     the
    1.80
     Dosis
    1.73
    鼴
    1.71
    frac
    1.70
    SaveChangesAsync
    1.69
     sibuk
    1.64
    )$
    1.63
     lanzó
    1.63
    Activations Density 0.010%
    No Known Activations