© 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. 1515
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and sequences

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

    The neuron is highly sensitive to long, multi-syllable technical terms (e.g. “visibility,” “properties,” “multicarrier”).

    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
     neumáticos
    -2.16
    揍
    -2.06
     juſ
    -2.03
     soyez
    -2.03
     bolsillos
    -1.96
     supprimer
    -1.95
     imprimer
    -1.93
     auriculares
    -1.93
     soportes
    -1.92
     rése
    -1.91
    POSITIVE LOGITS
     When
    2.27
    One
    2.25
    During
    2.23
     During
    2.20
     While
    2.19
     with
    2.17
     Before
    2.13
     In
    2.11
     in
    2.09
    There
    2.09
    Activations Density 0.494%

    No Known Activations