© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84009
    Prev
    Next
    INDEX
    Explanations

    hip resurfacing

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

    The neuron activates on appearances of the root “surface” (e.g. surface, surfaced, resurfaced), i.e. words denoting something coming to light or appearing.

    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
    as
    -2.72
    ⢮
    -2.17
    you
    -2.08
    かっこ
    -2.08
    躥
    -2.05
    หรือ
    -1.98
     اذا
    -1.98
     écrire
    -1.95
    ჱ
    -1.91
     ajoute
    -1.89
    POSITIVE LOGITS
    ’
    2.84
    ꪔ
    2.17
    …”
    2.13
    ,…
    2.13
    :
    2.11
    我先
    2.09
    ?”
    2.06
    ⑊
    2.06
    ,”
    2.03
    ……”
    2.03
    Activations Density 0.009%

    No Known Activations