© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71545
    Prev
    Next
    INDEX
    Explanations

    structured data formats

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

    This neuron activates on numeric literals (including integers and decimals) in code or data snippets.

    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
     of
    -1.30
     DEVICES
    -1.01
    cheibe
    -1.00
     корзи
    -1.00
     dager
    -1.00
     pictureBox
    -0.98
     fredag
    -0.98
    Ÿ
    -0.98
     onsdag
    -0.98
     layui
    -0.94
    POSITIVE LOGITS
     thậm
    0.98
    oczes
    0.96
     welchen
    0.88
    𝖾
    0.85
    綜合報導
    0.84
     verknüp
    0.84
     dokonce
    0.83
    izable
    0.82
     présents
    0.81
    ະ
    0.80
    Activations Density 0.003%

    No Known Activations