© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66493
    Prev
    Next
    INDEX
    Explanations

    seamless, effortless, flawless execution

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

    The neuron fires on occurrences of the word “seamless.”

    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
    皷
    -2.50
     Empfindung
    -2.42
     Gefühle
    -2.25
    ruguay
    -2.23
     Erkenntnisse
    -2.19
     Erkennt
    -2.19
    菹
    -2.19
     schnellen
    -2.16
    
    -2.13
    啬
    -2.09
    POSITIVE LOGITS
    or
    2.55
    x
    2.47
    that
    2.45
    櫺
    2.45
    He
    2.45
    v
    2.41
    摃
    2.41
    //
    2.41
    </b>
    2.39
    e
    2.39
    Activations Density 0.005%

    No Known Activations