© 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. 34-GEMMASCOPE-RES-131K
    7. 78162
    Prev
    Next
    INDEX
    Explanations

    speak to or with

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

    The neuron fires on words denoting someone talking or communicating (e.g. speak, spoke, spoken, talking, talked).

    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
    ग़
    -0.79
    bindParam
    -0.78
    であるが
    -0.73
    нансо
    -0.71
     показать
    -0.69
    رامی
    -0.67
    Leopard
    -0.67
     frambo
    -0.66
     choisissez
    -0.65
     commentaires
    -0.65
    POSITIVE LOGITS
     briefly
    1.04
     with
    1.02
     spoke
    1.01
     conversation
    0.98
     talk
    0.97
    talk
    0.96
     about
    0.90
     conversar
    0.87
     talks
    0.87
    TALK
    0.86
    Activations Density 0.010%

    No Known Activations