© 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. 9535
    Prev
    Next
    INDEX
    Explanations

    article followed by verb

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

    The neuron strongly activates on numeric expressions and quantitative indicators (e.g. digits, measurements, stats).

    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
    🏭
    -1.74
    饷
    -1.73
     Meksiko
    -1.61
    儼
    -1.53
    tionally
    -1.49
    卽
    -1.49
    ࣭
    -1.49
     syk
    -1.48
    madeus
    -1.46
    ergies
    -1.44
    POSITIVE LOGITS
     дошко
    1.72
     recursos
    1.38
    RUnlock
    1.31
     pensar
    1.23
    ıyors
    1.21
     Läng
    1.19
    𝗺
    1.18
    🪳
    1.17
    𝗼
    1.17
    実践
    1.17
    Activations Density 0.169%

    No Known Activations