© 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. 38835
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

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

    The neuron is picking up on PLY/Yacc parser code, i.e. imports of the ply.yacc module, the definition of the tokens list, and grammar‐rule functions whose names begin with “p_.”

    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
     mengen
    -1.53
    lapis
    -1.46
     my
    -1.45
     Veel
    -1.42
     Waar
    -1.40
    )
    -1.39
    ствовать
    -1.38
    klart
    -1.37
     fokus
    -1.36
     verdienen
    -1.36
    POSITIVE LOGITS
    </em>
    2.11
    StoryboardSegue
    1.63
     ramo
    1.45
     människor
    1.41
    あげて
    1.41
    上げて
    1.38
    características
    1.38
     anunciou
    1.37
    mejores
    1.37
    </h5>
    1.36
    Activations Density 0.001%

    No Known Activations