© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66092
    Prev
    Next
    INDEX
    Explanations

    HTML and code document starts

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

    The neuron fires on HTML/XML comment blocks, i.e. regions enclosed in “<!-- … -->.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    1
    -3.02
    (
    -2.59
    *
    -2.42
    <blockquote>
    -2.33
    <
    -2.27
    9
    -2.25
    4
    -2.19
    er
    -2.17
    <h2>
    -2.16
    8
    -2.16
    POSITIVE LOGITS
    ↵
    2.58
    谵
    2.25
    樘
    2.13
    ׅ
    2.13
    STALK
    2.09
     domov
    2.08
    狨
    2.08
    上司
    2.06
     conferencias
    2.06
    secutions
    2.05
    Activations Density 0.008%

    No Known Activations