© 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. 64365
    Prev
    Next
    INDEX
    Explanations

    stop or visiting

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

    This neuron fires on direct second-person address—instances of “you” (and related invitation/question constructions) speaking directly to the reader.

    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
    ruly
    -0.80
    zare
    -0.78
    катери
    -0.76
    chige
    -0.73
    allah
    -0.72
    willReturn
    -0.72
     Clément
    -0.71
    回来了
    -0.71
     }}">
    -0.70
    ServiceProvider
    -0.70
    POSITIVE LOGITS
     stop
    4.69
     Stop
    3.84
    Stop
    3.83
     stopping
    3.75
    stop
    3.73
     stopped
    3.66
     stops
    3.66
    Stopped
    2.78
    Stopping
    2.77
    STOP
    2.75
    Activations Density 0.059%

    No Known Activations