© 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. 70599
    Prev
    Next
    INDEX
    Explanations

    media outlets and publications

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

    The neuron activates on mentions of media or news outlets (e.g. the words “media outlets” or “news outlets”).

    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
    vantaged
    -1.77
    They
    -1.63
    躄
    -1.61
     about
    -1.59
    ượ
    -1.49
     on
    -1.48
    媜
    -1.48
    There
    -1.48
    .
    -1.43
    使用
    -1.43
    POSITIVE LOGITS
    is
    1.98
    k
    1.95
    t
    1.90
    c
    1.87
    ta
    1.78
    ty
    1.78
    ou
    1.77
     outlets
    1.76
    会被
    1.73
    ad
    1.72
    Activations Density 0.005%

    No Known Activations