© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71949
    Prev
    Next
    INDEX
    Explanations

    range and [a,b] boundaries

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

    The neuron fires on numeric tokens—i.e. literal numbers (integers or decimals) appearing in code or 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_22/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
     papp
    -0.79
    bliss
    -0.76
    Diem
    -0.74
     deep
    -0.74
    чатки
    -0.73
    colazione
    -0.71
    Lists
    -0.71
     poll
    -0.71
     BRASIL
    -0.71
    сили
    -0.70
    POSITIVE LOGITS
     range
    1.34
     Range
    1.16
    范围
    1.12
    range
    1.11
    Range
    1.09
    trange
    1.06
    RANGE
    1.04
     диапа
    1.03
    范围内
    1.02
     obszar
    1.01
    Activations Density 0.138%

    No Known Activations