© 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. 10-GEMMASCOPE-RES-131K
    7. 124073
    Prev
    Next
    INDEX
    Explanations

    introducing new or current events

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

    The neuron selectively activates on numeric expressions—digits, measurements, counts, and related quantifiers—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_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
     senere
    -1.11
    );
    -1.08
    oriya
    -1.06
    bulb
    -1.02
    ⁄
    -0.97
     on
    -0.96
     MacOS
    -0.94
    taler
    -0.93
     llamó
    -0.92
    picable
    -0.92
    POSITIVE LOGITS
     misericordia
    1.30
     balles
    1.24
     koja
    1.23
    Again
    1.20
    𓆏
    1.19
    
    1.18
     ulang
    1.18
     inolvid
    1.17
    圌
    1.17
     второй
    1.16
    Activations Density 0.059%

    No Known Activations