© 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. 34-GEMMASCOPE-RES-131K
    7. 102574
    Prev
    Next
    INDEX
    Explanations

    in its infancy

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

    This neuron activates on numeric tokens (numbers, years, counts) in the 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_34/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
    不变
    -0.92
     گذشته
    -0.89
    $^{\
    -0.88
    ğine
    -0.82
    AfterClass
    -0.79
    inking
    -0.79
     الماضي
    -0.79
    紲
    -0.79
     artık
    -0.79
     última
    -0.79
    POSITIVE LOGITS
     still
    3.06
    まだ
    2.47
     هنوز
    2.33
     ainda
    2.27
    はまだ
    2.23
     nascent
    2.23
     تازه
    2.22
     अभी
    2.20
     dopiero
    2.20
    still
    2.17
    Activations Density 0.148%

    No Known Activations