© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84275
    Prev
    Next
    INDEX
    Explanations

    .net project references

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

    The neuron activates on XML namespace and CLR‐namespace tokens (especially Microsoft.* URIs and assembly/version segments).

    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
     damen
    -1.30
     gese
    -1.19
     vogel
    -1.19
     schal
    -1.18
     inga
    -1.16
     minutter
    -1.16
     tages
    -1.16
     others
    -1.16
     medan
    -1.13
     nessun
    -1.12
    POSITIVE LOGITS
     Auffassung
    1.20
    توضیحات
    1.14
     Verhältnisse
    1.08
     Betrachtung
    1.08
     umfang
    1.07
     that
    1.06
    attendre
    1.06
     ഗ
    1.05
    ettbewer
    1.04
     beeindruck
    1.04
    Activations Density 0.072%

    No Known Activations