© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99176
    Prev
    Next
    INDEX
    Explanations

    who verb clause

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

    The neuron responds to numeric tokens, especially digit sequences and numbers (including those with decimal points).

    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
    SanPham
    -1.37
     jopa
    -1.36
    -
    -1.32
     cejas
    -1.30
     produite
    -1.24
    NhanVien
    -1.23
    ांकि
    -1.21
     Spaces
    -1.16
     всех
    -1.15
    ecco
    -1.15
    POSITIVE LOGITS
     this
    1.73
     since
    1.50
    borns
    1.45
    ことから
    1.42
    おわりに
    1.38
    neous
    1.35
     aliment
    1.34
     terap
    1.33
    enance
    1.31
    piratory
    1.30
    Activations Density 0.031%

    No Known Activations