© 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. 73942
    Prev
    Next
    INDEX
    Explanations

    XML tags and delimiters

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

    The neuron responds to individual punctuation tokens (e.g. slashes “/” or commas “,”).

    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
     for
    -1.20
     :{
    -0.97
     provocado
    -0.95
    პ
    -0.95
     when
    -0.93
    😳
    -0.93
     testGet
    -0.91
     défend
    -0.90
    😋
    -0.90
    ävät
    -0.90
    POSITIVE LOGITS
    ︐
    1.05
    どれだけ
    1.04
    痍
    1.02
    rather
    0.99
    感じで
    0.97
    य़
    0.96
    Dive
    0.95
    割と
    0.91
    <mask>
    0.91
     取り付け
    0.91
    Activations Density 0.000%

    No Known Activations