© 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. 67556
    Prev
    Next
    INDEX
    Explanations

    years, months, or numbers

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

    The neuron activates on numeric tokens, i.e. counts, measurements, dates, or other digit‐based quantities.

    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
     chegou
    -1.12
    ogramm
    -1.09
     generalmente
    -0.96
    上野
    -0.96
    previously
    -0.94
    pertory
    -0.94
     aberto
    -0.94
     reconoc
    -0.91
    Earlier
    -0.90
     conocidas
    -0.90
    POSITIVE LOGITS
    際には
    0.98
    個月
    0.95
    دکتر
    0.94
    愜
    0.91
     Speisen
    0.91
    ssl
    0.91
    :""
    0.89
     Prosecutor
    0.88
     perasaan
    0.88
    leşti
    0.87
    Activations Density 0.040%

    No Known Activations