© 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. 68795
    Prev
    Next
    INDEX
    Explanations

    sentence start words

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

    The neuron specializes in spotting numeric expressions—measurements, percentages, decimal values, or other numbers—in the text.

    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
     for
    -1.55
     doskon
    -1.44
    をお願い
    -1.33
     ajouté
    -1.31
    СКИ
    -1.29
    diseño
    -1.27
    Quercus
    -1.26
     inserire
    -1.25
     destacado
    -1.25
    をし
    -1.25
    POSITIVE LOGITS
     but
    1.53
    \
    1.45
     even
    1.36
     вас
    1.34
     to
    1.33
    lawesi
    1.28
     $+
    1.24
    gypti
    1.22
    TagMode
    1.22
     its
    1.21
    Activations Density 0.081%

    No Known Activations