© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72891
    Prev
    Next
    INDEX
    Explanations

    brunette descriptors

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

    This neuron fires strongly on special code/markup symbols—e.g. comment markers (“{#”, “<!--”) and LaTeX/math operators like “\odot.”

    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
    肫
    -2.80
    𞤢
    -2.67
     kompeti
    -2.63
    趼
    -2.38
    क्टर
    -2.36
     Meningkatkan
    -2.34
    菝
    -2.27
    CurtirCurtir
    -2.25
    皺
    -2.25
     klima
    -2.23
    POSITIVE LOGITS
     he
    2.42
     fiscales
    2.41
     pasó
    2.41
    on
    2.36
    𖣘
    2.25
     alrededores
    2.22
    se
    2.14
    料
    2.13
     ricorda
    2.08
     没有
    2.05
    Activations Density 0.001%

    No Known Activations