© 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. 1700
    Prev
    Next
    INDEX
    Explanations

    mythological figures and events

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

    This neuron fires on numerical quantities—especially decimal or specific measurement values—in the 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
    颪
    -1.41
     pensez
    -1.36
    最後に
    -1.35
     Quận
    -1.35
    ENGER
    -1.34
     alrededores
    -1.31
     médecins
    -1.30
     jardines
    -1.29
    INOS
    -1.27
    instellungen
    -1.27
    POSITIVE LOGITS
     for
    2.11
    f
    1.47
     what
    1.34
    g
    1.31
    h
    1.31
    l
    1.28
     on
    1.27
     will
    1.23
    ’
    1.22
    what
    1.20
    Activations Density 0.144%

    No Known Activations