© 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. 72788
    Prev
    Next
    INDEX
    Explanations

    functional equations, variational problems, claims

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

    The neuron activates on occurrences of “functional” (and its plural “functionals”) in scientific text.

    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
     anadolu
    -1.52
     aici
    -1.42
    一愣
    -1.42
     The
    -1.42
     sparrows
    -1.41
     titolata
    -1.40
     tracción
    -1.38
    gradable
    -1.36
    ⣉
    -1.35
    🅣
    -1.32
    POSITIVE LOGITS
    er
    1.63
    -
    1.63
    ro
    1.60
    af
    1.59
    se
    1.59
    ub
    1.57
    oo
    1.55
    _
    1.52
    “
    1.52
     the
    1.50
    Activations Density 0.025%

    No Known Activations