© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84060
    Prev
    Next
    INDEX
    Explanations

    Xamarin.Forms, Michele, Norton

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

    The neuron specifically detects occurrences of the term “Xamarin” (e.g. in namespaces or schema URLs).

    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
     reúne
    -2.67
    zelfde
    -2.67
    蹀
    -2.63
    Toluene
    -2.59
    Barium
    -2.55
     inauguración
    -2.53
    actéristi
    -2.50
    之为
    -2.44
     blauw
    -2.39
     ſmall
    -2.38
    POSITIVE LOGITS
    A
    2.78
    に
    2.70
    ↵↵
    2.67
    C
    2.42
    after
    2.34
    when
    2.34
    n
    2.34
    l
    2.33
     To
    2.30
    you
    2.28
    Activations Density 0.007%

    No Known Activations