© 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. 22-GEMMASCOPE-RES-131K
    7. 72479
    Prev
    Next
    INDEX
    Explanations

    x and y coordinates

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

    The neuron fires on numeric literals in code—especially array‐index numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    isasi
    -1.24
     about
    -1.16
    cketed
    -1.09
     dinoss
    -1.07
     Zitron
    -1.06
     viewWillAppear
    -1.05
    ckeye
    -1.05
    糁
    -1.05
     internetowa
    -1.05
     lác
    -1.03
    POSITIVE LOGITS
     where
    1.45
     locations
    1.11
     it
    1.04
     will
    0.96
     for
    0.92
    lamó
    0.91
    ֩
    0.91
    It
    0.90
     could
    0.90
    zeh
    0.90
    Activations Density 0.006%

    No Known Activations