© 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. 130413
    Prev
    Next
    INDEX
    Explanations

    exercise • love • share • note • chief

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

    The neuron primarily activates on numeric tokens (numbers and numeric measurements) and related punctuation.

    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
     neuve
    -1.61
    蛧
    -1.45
    iltà
    -1.41
    әһ
    -1.41
     estekak
    -1.34
    ведь
    -1.33
    исленность
    -1.32
    //!
    -1.31
     Each
    -1.30
     думаете
    -1.30
    POSITIVE LOGITS
     then
    2.14
     исчез
    1.25
     vervolgens
    1.23
     certamente
    1.19
     tentativo
    1.18
     either
    1.17
     diverso
    1.17
     or
    1.17
     this
    1.16
    の見
    1.16
    Activations Density 0.214%

    No Known Activations