© 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. 10-GEMMASCOPE-RES-131K
    7. 124608
    Prev
    Next
    INDEX
    Explanations

    common words and phrases

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

    The neuron fires on LaTeX macro names and related counter/theorem commands (i.e. control‐sequence tokens).

    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
     jule
    -1.26
     cend
    -1.25
     مناف
    -1.17
     centrum
    -1.13
     poud
    -1.13
     sosi
    -1.13
     lyd
    -1.13
     friv
    -1.12
     rekord
    -1.12
     CLOSED
    -1.12
    POSITIVE LOGITS
     its
    2.25
     делает
    1.56
     a
    1.48
    ة
    1.47
     has
    1.38
     powinno
    1.34
    eclampsia
    1.33
    .
    1.33
    setcounter
    1.29
     miał
    1.28
    Activations Density 0.011%

    No Known Activations