© 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. 38700
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

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

    This neuron detects the punctuation and numeric tokens used to mark items in a numbered or ordered list.

    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
     this
    -1.83
     their
    -1.64
     about
    -1.47
     funcionando
    -1.37
     sentado
    -1.35
     Jerusalén
    -1.33
     cantando
    -1.31
    ⽼
    -1.29
    所以在
    -1.28
    ')";
    -1.27
    POSITIVE LOGITS
    :
    1.55
    \
    1.33
    Etimología
    1.33
     also
    1.28
    𝔄
    1.20
     através
    1.19
    錯誤
    1.16
     according
    1.16
     durch
    1.16
    我們
    1.15
    Activations Density 0.164%

    No Known Activations