© 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. 34-GEMMASCOPE-RES-131K
    7. 98916
    Prev
    Next
    INDEX
    Explanations

    transmit/send information

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

    The neuron activates on formal court‐opinion header and boilerplate terms (e.g. “Memorandum Opinion,” “copy is attached,” “Transmitted,” 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
    зован
    -0.74
    čku
    -0.70
    Gid
    -0.67
    ôm
    -0.66
     vär
    -0.66
    newData
    -0.66
    chomp
    -0.64
     resus
    -0.64
    zył
    -0.64
    atoren
    -0.63
    POSITIVE LOGITS
     transmitted
    3.45
     transmit
    3.25
     transmission
    3.08
     send
    2.97
     sent
    2.94
     sending
    2.80
     transmitting
    2.73
    send
    2.72
     forwarded
    2.72
     transmits
    2.67
    Activations Density 0.091%

    No Known Activations