© 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. 77739
    Prev
    Next
    INDEX
    Explanations

    writers and contributors

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

    The neuron detects mentions of people’s professional roles or occupations (e.g., journalist, writer, editor, columnist) in author‐byline or bio sections.

    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
     wektor
    -0.74
    PAGES
    -0.74
    ને
    -0.74
    {}{}
    -0.72
     only
    -0.69
     enthalten
    -0.68
    interess
    -0.68
    WhatsApp
    -0.66
    disciplinar
    -0.66
     instruments
    -0.66
    POSITIVE LOGITS
     contributor
    2.75
     contributors
    2.63
     contributing
    2.53
     writing
    2.31
     writers
    2.25
     Contributing
    2.23
     contributions
    2.20
     contributed
    2.20
     contribute
    2.19
    Contributing
    2.17
    Activations Density 0.105%

    No Known Activations