© 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. 8086
    Prev
    Next
    INDEX
    Explanations

    ni, NI, nether, Nil

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

    The neuron detects numeric tokens (numbers, especially multi‐digit and decimal values).

    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
    R
    -3.25
    ”，
    -2.55
    ET
    -2.52
    AR
    -2.48
    B
    -2.42
    OS
    -2.42
    EM
    -2.41
    S
    -2.33
    ஂ
    -2.31
    ↑↑↑</
    -2.22
    POSITIVE LOGITS
     Aufgrund
    2.50
     "
    2.50
    ните
    2.48
    то
    2.36
     Während
    2.31
    ieuses
    2.19
     Obwohl
    2.19
    ні
    2.19
    绉
    2.16
    ised
    2.14
    Activations Density 0.001%

    No Known Activations