© 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. 595
    Prev
    Next
    INDEX
    Explanations

    web development libraries and dependencies

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

    The neuron detects and highlights text inside HTML comment blocks (i.e., anything between “<!--” and “-->”).

    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
     vijf
    -1.31
    lentes
    -1.30
     séries
    -1.27
    𓆏
    -1.23
     fazenda
    -1.23
     unicórnio
    -1.21
     adesivo
    -1.19
     constitue
    -1.18
     algas
    -1.18
     sympa
    -1.17
    POSITIVE LOGITS
     högre
    1.60
     främ
    1.27
     ändå
    1.22
     långt
    1.20
     vanligt
    1.19
     especially
    1.09
     båda
    1.08
     sparkly
    1.08
     istället
    1.07
    w
    1.06
    Activations Density 0.009%

    No Known Activations