© 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. 101762
    Prev
    Next
    INDEX
    Explanations

    University names

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

    The neuron fires on numeric tokens or numeric expressions (e.g. standalone numbers, decimal values, or multi‐digit numerals).

    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
    总部
    -1.38
     撮り
    -1.30
     campeones
    -1.27
     jiné
    -1.25
     entreprise
    -1.25
    以上就是
    -1.23
     ||
    -1.22
    还有一
    -1.22
     vender
    -1.21
     kalite
    -1.21
    POSITIVE LOGITS
     founded
    1.36
    ECM
    1.24
    如果
    1.24
     than
    1.23
     learned
    1.20
     ‘
    1.20
    哭了
    1.20
     enabled
    1.19
     learnt
    1.19
     each
    1.16
    Activations Density 0.515%

    No Known Activations