© 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. 1877
    Prev
    Next
    INDEX
    Explanations

    specific places and entities

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

    The neuron responds to numeric tokens in the text—especially measurements or counts written as numbers (including decimals).

    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
     Dingen
    -1.57
     zijne
    -1.57
    ateurs
    -1.48
     gracios
    -1.46
     Projektu
    -1.45
    eczki
    -1.42
     musíte
    -1.38
     belki
    -1.38
    زندگی
    -1.37
     hunne
    -1.36
    POSITIVE LOGITS
     by
    2.28
     three
    1.55
     to
    1.55
     where
    1.54
     nuovi
    1.46
     of
    1.44
     for
    1.43
     these
    1.39
     newly
    1.38
     as
    1.37
    Activations Density 0.099%

    No Known Activations