© 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. 75409
    Prev
    Next
    INDEX
    Explanations

    on place names

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

    The neuron detects decimal or floating-point numeric measurements (numbers with a decimal point).

    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
    mendous
    -1.50
    ächst
    -1.48
     things
    -1.43
     Перейти
    -1.38
    ,”
    -1.38
     variations
    -1.34
    дения
    -1.33
     become
    -1.32
    だそうです
    -1.31
     všem
    -1.31
    POSITIVE LOGITS
     the
    1.60
     Each
    1.45
    2
    1.44
    3
    1.36
    5
    1.35
    FFFFFF
    1.34
    between
    1.32
     sehingga
    1.32
     gewüns
    1.31
     between
    1.30
    Activations Density 0.063%

    No Known Activations