© 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. 22-GEMMASCOPE-RES-131K
    4. 13353
    Prev
    Next
    INDEX
    Explanations

    adjective followed by noun

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

    The neuron activates on tokens that are part of numeric values or quantitative expressions (e.g. digits, decimals, concentrations, counts).

    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
     söyl
    -1.01
    apartament
    -0.94
    そうですが
    -0.89
    Klasse
    -0.88
    ترة
    -0.86
    Acl
    -0.85
     tartalmaz
    -0.84
    Polska
    -0.84
    dámské
    -0.84
    憚
    -0.84
    POSITIVE LOGITS
    :";
    1.09
     buurt
    1.00
     ";
    0.94
     прове
    0.91
    0
    0.91
    setcounter
    0.88
    └──
    0.87
    :",
    0.86
    this
    0.86
     This
    0.85
    Activations Density 0.075%

    No Known Activations