© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73170
    Prev
    Next
    INDEX
    Explanations

    suffixes like ovec, oski, ica

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

    This neuron fires on segments of capitalized proper names (people and places) in the text.

    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
     That
    -2.88
    '
    -2.77
     This
    -2.45
     What
    -2.33
     "
    -2.31
    蜮
    -2.30
     keterangan
    -2.22
    。"
    -2.17
    !?"
    -2.17
     The
    -2.14
    POSITIVE LOGITS
    艄
    2.38
    ᜀ
    2.34
     fotografías
    2.25
    鏟
    2.23
     calme
    2.23
    </h3>
    2.17
    なければ
    2.08
    繰り返
    2.08
    臯
    2.06
    一个月
    2.03
    Activations Density 0.060%

    No Known Activations