© 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. 90983
    Prev
    Next
    INDEX
    Explanations

    reporting and media coverage

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

    The neuron responds strongly to language about the press’s right to publish news, information, and opinions (i.e. free‐speech/press‐freedom wording).

    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
     alumnos
    -0.92
    óf
    -0.90
    rowData
    -0.89
    zbęd
    -0.81
    EmailAddress
    -0.80
    圣节
    -0.78
    hists
    -0.77
    herokuapp
    -0.77
    corer
    -0.76
    aol
    -0.74
    POSITIVE LOGITS
     reporting
    2.86
     coverage
    2.36
    reporting
    2.20
     news
    2.06
     report
    2.03
    Reporting
    1.99
     Reporting
    1.95
     reportage
    1.90
     reported
    1.88
     sensational
    1.88
    Activations Density 0.065%

    No Known Activations