© 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. 116450
    Prev
    Next
    INDEX
    Explanations

    people enjoy their activities

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

    The neuron fires on personal‐reference tokens—proper names and personal pronouns—marking sections of biographical or self‐referential 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
    各
    -0.81
    libft
    -0.81
     dormitórios
    -0.80
    ⍺
    -0.80
    vex
    -0.77
     verwalten
    -0.77
    insley
    -0.77
    ceil
    -0.77
     presencia
    -0.76
    GMENT
    -0.75
    POSITIVE LOGITS
     enjoy
    3.17
     enjoys
    2.77
     Enjoy
    2.47
    enjoy
    2.47
     enjoyed
    2.47
    Enjoy
    2.42
     enjoying
    2.41
     hobbies
    2.23
     enjoyment
    2.11
     interests
    1.80
    Activations Density 0.018%

    No Known Activations