© 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. 113131
    Prev
    Next
    INDEX
    Explanations

    lob, lop, Dox

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

    This neuron activates on occurrences of the character sequence “lob” (e.g. in “Lobos,” “lobular,” “lobulated,” “lobule,” etc.).

    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
    珦
    -2.98
    ﮩ
    -2.72
    蹌
    -2.55
    ς
    -2.50
     It
    -2.48
    нутрен
    -2.38
    ⬯
    -2.36
     مفص
    -2.34
    那我
    -2.30
    ſelf
    -2.28
    POSITIVE LOGITS
    -
    3.36
    1
    2.94
     '
    2.89
    "
    2.83
    /
    2.83
     totalmente
    2.25
    天生
    2.23
     evergreen
    2.13
     sporad
    2.13
     ahora
    2.11
    Activations Density 0.006%

    No Known Activations