© 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. 22-GEMMASCOPE-RES-131K
    7. 35867
    Prev
    Next
    INDEX
    Explanations

    technical terms followed by descriptors

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

    The neuron activates strongly on specialized technical or domain-specific nouns (e.g. material names, component identifiers, code class/field names).

    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
     denaro
    -0.99
    年も
    -0.97
     aktualisiert
    -0.95
     creencias
    -0.94
     sustancias
    -0.94
    ほとん
    -0.91
     località
    -0.91
     vorigen
    -0.90
     élevés
    -0.90
     étroite
    -0.90
    POSITIVE LOGITS
     for
    1.22
     in
    1.18
    соеди
    1.16
     to
    1.09
     of
    1.08
     Sebagai
    0.99
     proxy
    0.94
     when
    0.91
     detection
    0.91
    erobic
    0.90
    Activations Density 0.171%

    No Known Activations