© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 16336
    Prev
    Next
    INDEX
    Explanations

    journalistic review

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

    This neuron detects references to news or media outlets and coverage (e.g. mentions of “news,” “Fox News,” “local news,” “media,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ores
    0.77
    k
    0.75
     nucleation
    0.73
    centroid
    0.73
    ཡ
    0.73
     nugget
    0.72
    都
    0.72
     fastener
    0.71
     centroid
    0.71
        
    0.70
    POSITIVE LOGITS
     تلویزی
    1.69
     journalistic
    1.68
     Journalists
    1.68
     journalists
    1.65
     journalism
    1.65
     Television
    1.60
     журнали
    1.59
     télévision
    1.59
    television
    1.58
    newspaper
    1.55
    Activations Density 1.140%

    No Known Activations