© 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. 58533
    Prev
    Next
    INDEX
    Explanations

    mathematics and programming abbreviations

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

    The neuron strongly activates on very short alphabetic tokens—mostly one‐ or two‐letter sequences.

    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
    <td>
    -1.87
    <bos>
    -1.77
    L
    -1.68
    F
    -1.68
    气氛
    -1.61
    ↵
    -1.58
     mismas
    -1.53
     wth
    -1.52
     proactively
    -1.48
     elegancia
    -1.48
    POSITIVE LOGITS
    杳
    1.78
    публи
    1.73
     These
    1.73
     Ihren
    1.67
    izzate
    1.66
     принад
    1.55
    bunifu
    1.55
    BeNil
    1.55
    窒
    1.53
     if
    1.52
    Activations Density 0.030%

    No Known Activations