© 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. 12651
    Prev
    Next
    INDEX
    Explanations

    or / separators

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

    This neuron detects slash punctuation ("/") used to join or separate terms in technical compound expressions.

    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
    两种
    -1.27
    ">)</
    -1.25
     or
    -1.25
    "]))
    -1.22
    iks
    -1.13
     ТА
    -1.13
    '),
    -1.12
     PPE
    -1.11
    unjuk
    -1.10
    novu
    -1.09
    POSITIVE LOGITS
     which
    1.34
     soste
    1.27
     ulei
    1.19
     your
    1.16
     our
    1.16
     mães
    1.15
     these
    1.10
     giardino
    1.09
     escolas
    1.09
     vostre
    1.07
    Activations Density 0.216%

    No Known Activations