© 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. 76652
    Prev
    Next
    INDEX
    Explanations

    talking about

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

    This neuron specifically detects the verb “talk” (including “talking”) in the text.

    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
     bezeichneter
    -0.82
    bazel
    -0.81
    ADORA
    -0.79
    рюкзак
    -0.78
    érique
    -0.77
    Retorno
    -0.77
    TICKET
    -0.76
    adores
    -0.76
     talking
    -0.75
     similaires
    -0.75
    POSITIVE LOGITS
     shop
    1.46
     strategy
    1.38
    shop
    1.36
     politics
    1.35
     to
    1.29
     turkey
    1.27
    Shop
    1.23
     more
    1.20
     logistics
    1.17
     tactics
    1.11
    Activations Density 0.012%

    No Known Activations