© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108081
    Prev
    Next
    INDEX
    Explanations

    news and politics

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

    The neuron fires strongly on capitalized named entities—such as people’s names, organizations, places, and acronyms.

    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
     أيضًا
    -1.88
     آنها
    -1.70
    わかる
    -1.65
     honored
    -1.63
     theater
    -1.56
     flavors
    -1.53
    ًا
    -1.52
    わかり
    -1.51
     behavior
    -1.49
    behavior
    -1.49
    POSITIVE LOGITS
     всё
    2.34
     sólo
    2.30
     labour
    2.09
     tumour
    2.05
     vapour
    2.05
     humour
    2.03
     neighbourhoods
    2.03
     honour
    2.03
     odour
    2.03
     colour
    1.98
    Activations Density 1.159%

    No Known Activations