© 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. 65147
    Prev
    Next
    INDEX
    Explanations

    javadoc documentation

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

    The neuron activates strongly on HTML/XML comment openers (“<!--”), i.e. the start of comments in markup.

    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
    s
    -2.70
     prioriti
    -1.89
    焄
    -1.84
    だが
    -1.81
     have
    -1.77
    er
    -1.71
    ﾋ
    -1.70
    UGHTER
    -1.70
     because
    -1.69
     before
    -1.68
    POSITIVE LOGITS
     This
    2.23
     gikk
    2.16
    ak
    2.13
     câbles
    2.13
     verdaderos
    2.06
     !!!!
    2.05
    щита
    2.05
    秾
    1.93
    ISSUE
    1.93
    ﮨ
    1.90
    Activations Density 0.005%

    No Known Activations