© 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. 10-GEMMASCOPE-RES-131K
    7. 44772
    Prev
    Next
    INDEX
    Explanations

    reporters and media personnel

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

    The neuron activates on words signaling press interactions—mentions of reporters, media, interviews, and press conferences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     four
    -1.85
     $
    -1.73
     many
    -1.63
     on
    -1.63
     of
    -1.61
     three
    -1.55
     Recently
    -1.53
     in
    -1.52
     Some
    -1.51
     и
    -1.50
    POSITIVE LOGITS
     nejsou
    1.45
     Ii
    1.45
     HYPER
    1.44
     kardashian
    1.44
     NEGATIVE
    1.42
     REASONS
    1.42
     catégories
    1.41
     THOUS
    1.41
     SAIL
    1.41
     extraordinaire
    1.40
    Activations Density 0.033%

    No Known Activations