© 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. 38375
    Prev
    Next
    INDEX
    Explanations

    news sources

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

    The neuron activates on occurrences of the word “news,” i.e. tokens marking news sources or headlines.

    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
     news
    -1.10
    收购
    -0.77
     jornalista
    -0.72
     denial
    -0.72
    ンプ
    -0.70
     território
    -0.70
    を搭載
    -0.68
     deny
    -0.68
    ABOVE
    -0.68
     dilakukan
    -0.67
    POSITIVE LOGITS
    room
    0.97
     katika
    0.96
    ঢ
    0.86
     Ust
    0.84
    jaar
    0.84
    꺽
    0.82
    ica
    0.82
     devam
    0.81
     продолжа
    0.81
    thal
    0.80
    Activations Density 0.024%

    No Known Activations