© 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. 10-GEMMASCOPE-RES-131K
    7. 21846
    Prev
    Next
    INDEX
    Explanations

    Les Paul, Noah, mycobacteria

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

    proper nouns and names, particularly biblical, musical, and geographical names.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron spikes on named entities—proper names, places, brand/product names, biblical figures, and technical 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_10/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
     to
    -2.53
     will
    -2.28
     since
    -1.98
    ቍ
    -1.91
     as
    -1.88
     always
    -1.88
     usually
    -1.84
    what
    -1.77
     now
    -1.75
     would
    -1.70
    POSITIVE LOGITS
     wth
    1.79
     médicaments
    1.65
     uſed
    1.64
    weren
    1.62
     venant
    1.62
     totalement
    1.59
     marchandises
    1.57
    甶
    1.54
     cérami
    1.54
     debacle
    1.50
    Activations Density 0.015%

    No Known Activations