© 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. 11813
    Prev
    Next
    INDEX
    Explanations

    Balanced states and processes

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

    The neuron fires strongly on occurrences of the word “balanced.”

    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
     The
    -3.00
     ''
    -2.91
     algunas
    -2.77
     Algunas
    -2.69
     komplette
    -2.67
     És
    -2.58
     Provides
    -2.50
    ⟣
    -2.47
     alcune
    -2.39
     
    -2.38
    POSITIVE LOGITS
    This
    2.42
     祝福
    2.42
     pushes
    2.42
    !(
    2.31
    𓋼
    2.28
    에서는
    2.27
    !”
    2.27
    While
    2.25
    𓄹
    2.22
    ?’
    2.20
    Activations Density 0.007%

    No Known Activations