© 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. 69084
    Prev
    Next
    INDEX
    Explanations

    code and markup structures

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

    This neuron responds to punctuation separators—especially hyphens (and similar characters like colons)—in HTML/XML tag or attribute names.

    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
     to
    -1.52
     cima
    -1.30
    更高的
    -1.26
    buttonStyle
    -1.20
    鹵
    -1.13
    」、「
    -1.13
    énd
    -1.12
     باید
    -1.10
     Tó
    -1.09
    𓇼
    -1.06
    POSITIVE LOGITS
     síntomas
    1.18
    いま
    1.18
    自分が
    1.14
    u
    1.12
     fatores
    1.12
    美好的
    1.11
     ,.
    1.11
     rendimiento
    1.10
     conteúdos
    1.09
    already
    1.09
    Activations Density 0.012%

    No Known Activations