© 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. 67617
    Prev
    Next
    INDEX
    Explanations

    PDO ASSOC fetch

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

    The neuron is strongly triggered by numeric literals (integer or floating‐point constants) in code.

    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
    {
    -1.71
     (“
    -1.59
    </i>
    -1.48
     (‘
    -1.48
    ↵↵↵
    -1.46
     

    -1.37
    ↵↵↵↵↵↵
    -1.35
     réalisées
    -1.34
     “
    -1.34
    伫
    -1.33
    POSITIVE LOGITS
    赑
    1.64
    ଝ
    1.59
     verhind
    1.55
    塒
    1.51
    自分の
    1.48
    rollers
    1.48
     microondas
    1.48
    噐
    1.48
    tonsoft
    1.46
    鹮
    1.46
    Activations Density 0.007%

    No Known Activations