© 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. 69225
    Prev
    Next
    INDEX
    Explanations

    introduces content

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

    The neuron specifically detects the LaTeX `\mbox` command.

    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
    uré
    -1.18
     coque
    -1.16
    깐
    -1.14
    GetAxis
    -1.13
     rapporter
    -1.11
    ologiques
    -1.09
     carnaval
    -1.08
     héroes
    -1.08
     comité
    -1.06
     baratas
    -1.06
    POSITIVE LOGITS
     verkauft
    1.05
     используются
    1.01
     estrictamente
    1.00
     Beobachtungen
    0.99
    N
    0.97
    every
    0.94
     geliefert
    0.93
    The
    0.93
     твое
    0.93
     ഒരു
    0.93
    Activations Density 0.000%

    No Known Activations