© 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. 109114
    Prev
    Next
    INDEX
    Explanations

    reporting speech from Israel

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

    The neuron fires on proper-name tokens—names of people, places, organizations, publications, dates, etc.

    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
    zło
    -0.79
     Historian
    -0.70
     ReactDOM
    -0.70
     Україн
    -0.69
     Yugoslav
    -0.65
    Nigerian
    -0.65
    Arrays
    -0.65
    ハンバーグ
    -0.65
    תח
    -0.64
    睁
    -0.64
    POSITIVE LOGITS
    ETER
    0.83
    ŚĆ
    0.80
    eter
    0.80
     incredible
    0.77
    WT
    0.76
     Denn
    0.76
    嶽
    0.74
    Tj
    0.73
    웨
    0.73
     креди
    0.73
    Activations Density 0.018%

    No Known Activations