© 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. 128630
    Prev
    Next
    INDEX
    Explanations

    group policy settings

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

    The neuron fires on tokens that are Microsoft systems‐management product names or their acronyms (e.g. WMI, SMS, SCCM, Intune).

    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
     totale
    -1.25
    t
    -1.24
     netto
    -1.20
     skak
    -1.17
     volle
    -1.16
     catégories
    -1.15
    把自己
    -1.15
    often
    -1.15
    geladen
    -1.14
     definida
    -1.14
    POSITIVE LOGITS
     sowohl
    1.54
     take
    1.53
    Both
    1.51
     zarówno
    1.48
    المنا
    1.42
     both
    1.40
    anyak
    1.29
     require
    1.25
     communicate
    1.24
     accompany
    1.21
    Activations Density 0.095%

    No Known Activations