© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 86889
    Prev
    Next
    INDEX
    Explanations

    seek or request

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

    The neuron responds to direct-address pronouns—especially “you” (and to a lesser extent “we”) when the text is speaking directly to the reader or audience.

    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
    kirakan
    -0.84
     LatLng
    -0.80
    criterion
    -0.79
    把
    -0.79
     сыром
    -0.75
     sice
    -0.75
    になります
    -0.74
     kiel
    -0.73
     lẽ
    -0.72
    ȁ
    -0.72
    POSITIVE LOGITS
     seek
    4.59
     seeks
    4.16
    seek
    3.45
     seeking
    3.34
     Seek
    3.23
     sought
    3.19
    Seek
    3.19
    Seeking
    2.59
    seeking
    2.59
    SEEK
    2.47
    Activations Density 0.124%

    No Known Activations