© 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. 73224
    Prev
    Next
    INDEX
    Explanations

    proper noun followed by punctuation or noun

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

    The neuron specifically fires on the token “vars,” as seen in the ESLint comment `no-unused-vars`.

    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
     to
    -1.29
    UMBIA
    -0.96
    ться
    -0.96
     include
    -0.95
    ICIAS
    -0.95
    ingeki
    -0.94
     小学生
    -0.93
    including
    -0.91
    UNDE
    -0.91
     Includes
    -0.90
    POSITIVE LOGITS
    都已经
    1.34
     manquer
    1.00
    톈
    0.99
    ppure
    0.98
    ihnachten
    0.96
    .
    0.96
     hinsichtlich
    0.96
    ┝
    0.96
     دى
    0.94
     bloques
    0.94
    Activations Density 0.000%

    No Known Activations