© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85795
    Prev
    Next
    INDEX
    Explanations

    information processing

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

    The neuron especially fires on occurrences of the word “Information” (and nearby numeric measurement tokens) in scientific reporting.

    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
     a
    -1.80
    \
    -1.65
     малень
    -1.34
     magasiner
    -1.32
     tirs
    -1.30
     vanden
    -1.30
     masaje
    -1.29
     béisbol
    -1.29
    ##
    -1.27
     kong
    -1.24
    POSITIVE LOGITS
     bereits
    1.77
     einzelnen
    1.53
     специфи
    1.46
     stemming
    1.41
    できません
    1.40
     pueden
    1.37
     anbieten
    1.34
     existing
    1.32
     Semua
    1.32
     hará
    1.30
    Activations Density 0.036%

    No Known Activations