© 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. 10-GEMMASCOPE-RES-131K
    4. 48010
    Prev
    Next
    INDEX
    Explanations

    time or points

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

    This neuron detects numeric expressions and quantity-related phrases (e.g., numbers, “one time,” “at one point,” “at his peak,” and similar measures).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    raires
    -1.09
    tungen
    -1.09
    そこから
    -1.05
    ulir
    -1.04
     teis
    -1.04
     炖
    -1.02
    Hvordan
    -1.02
    www
    -1.02
     maksi
    -1.01
    鯔
    -1.01
    POSITIVE LOGITS
    وزيع
    1.22
     língua
    1.15
    și
    1.15
    𝟑
    1.13
     könnt
    1.13
    ]:
    1.09
     employed
    1.09
     simply
    1.09
     просто
    1.09
    ̍t
    1.06
    Activations Density 0.081%

    No Known Activations