© 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. 42169
    Prev
    Next
    INDEX
    Explanations

    algebraic properties and geometry

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

    The neuron activates on occurrences of the word “algebraic.”

    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
    ᯾
    -2.84
    橚
    -2.73
    .
    -2.64
    </h2>
    -2.58
     cinque
    -2.58
    神情
    -2.56
    ༷
    -2.55
     distin
    -2.47
     somewhat
    -2.41
     semelh
    -2.33
    POSITIVE LOGITS
    COLN
    2.36
     säker
    2.36
    􀂃
    2.36
    section
    2.34
     到着
    2.33
     даже
    2.30
     meagre
    2.27
     optimise
    2.25
     oust
    2.25
     wiederhol
    2.23
    Activations Density 0.006%

    No Known Activations