© 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. 75026
    Prev
    Next
    INDEX
    Explanations

    differential geometry notation and concepts

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

    The neuron strongly activates on LaTeX‐style mathematical notation (math‐mode tokens and formula symbols).

    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
    ּוֹ
    -1.36
     to
    -1.30
    http
    -1.21
     ngunit
    -1.21
     after
    -1.18
     http
    -1.17
     guerres
    -1.16
    poptosis
    -1.16
     and
    -1.15
     After
    -1.14
    POSITIVE LOGITS
    所有的
    1.67
    klare
    1.36
    Genial
    1.33
    quien
    1.31
    diven
    1.26
    Willkommen
    1.25
     ajutor
    1.24
    ığınız
    1.23
    gebnis
    1.22
     effetto
    1.22
    Activations Density 0.119%

    No Known Activations