© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67245
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation

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

    The neuron activates on multi‐line comment delimiters (e.g. Python triple quotes or C‐style /* … */).

    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
    ځ
    -1.09
    pantalón
    -1.08
     zweimal
    -1.06
     hauptsächlich
    -1.05
    URERS
    -1.03
     χρησιμοποι
    -1.02
    SceneManagement
    -1.01
    IQUES
    -1.00
     necessario
    -1.00
    logica
    -0.98
    POSITIVE LOGITS
    )
    1.21
    .
    1.09
    </em>
    1.04
    ).
    0.96
    🕔
    0.94
     ませ
    0.93
     accidentes
    0.92
    "
    0.91
    guiar
    0.90
    ,
    0.90
    Activations Density 0.006%

    No Known Activations