© 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. 64992
    Prev
    Next
    INDEX
    Explanations

    js, angularjs, expressjs, pandas

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

    This neuron responds to multi-letter uppercase sequences, i.e. acronyms and initialisms.

    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
     they
    -2.03
     parseFrom
    -1.60
     for
    -1.44
     consentimento
    -1.32
    灕
    -1.28
     nampak
    -1.27
     importantes
    -1.27
     werdet
    -1.23
     was
    -1.21
     other
    -1.21
    POSITIVE LOGITS
     húmedo
    1.48
     its
    1.35
     fournisseurs
    1.32
    وفق
    1.29
     prends
    1.26
     facteurs
    1.25
     magasins
    1.25
     Lagi
    1.23
    ᐅ
    1.21
    ถ้า
    1.20
    Activations Density 0.120%

    No Known Activations