© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67010
    Prev
    Next
    INDEX
    Explanations

    starts of code blocks /**

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

    This neuron flags natural-language comment or documentation phrases in code (e.g. explanatory comments and template instructions).

    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
     kanton
    -1.31
     boden
    -1.19
     EconPapers
    -1.14
     souver
    -1.13
     Taille
    -1.11
     mídia
    -1.09
    си
    -1.09
     geheim
    -1.08
     verhind
    -1.08
     également
    -1.08
    POSITIVE LOGITS
     since
    1.19
    Vä
    1.13
     this
    1.13
     during
    1.09
     had
    1.08
     went
    1.06
     if
    1.03
     while
    1.02
    伟大
    1.02
    Probl
    1.02
    Activations Density 0.003%

    No Known Activations