© 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. 36626
    Prev
    Next
    INDEX
    Explanations

    Monday, Q, The, Plasma, Massachusetts

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

    The neuron strongly activates on standalone numeric tokens (in this case the digit “1”).

    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
     avez
    -1.23
    喻
    -1.20
    鄰
    -1.15
    多かった
    -1.10
    定価
    -1.09
     cómodo
    -1.09
    NOTIFY
    -1.09
     écoute
    -1.08
     exceptionnel
    -1.08
    をしています
    -1.07
    POSITIVE LOGITS
    があり
    1.35
    尔的
    1.20
    などを
    1.18
    weightedMode
    1.15
    WaitGroup
    1.10
    ですが
    1.10
     aprobó
    1.10
    そして
    1.08
    なども
    1.07
     is
    1.05
    Activations Density 0.000%

    No Known Activations