© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27271
    Prev
    Next
    INDEX
    Explanations

    fact that, vehicles require, Q:

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

    The neuron selectively responds to formal discourse markers and reporting verbs (e.g. question, fact, wondered, said, would, report) in a meeting‐minutes or parliamentary context.

    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
     zwykle
    -1.38
     все
    -1.30
     See
    -1.27
     wciąż
    -1.27
     también
    -1.23
     tiež
    -1.22
     vedno
    -1.22
     nebst
    -1.21
     généralement
    -1.20
     ее
    -1.18
    POSITIVE LOGITS
     poliuret
    1.34
     organik
    1.30
    temperatura
    1.30
     进行
    1.30
     pangan
    1.27
    でございます
    1.27
     profond
    1.25
     itinerario
    1.21
     informations
    1.21
     sentada
    1.20
    Activations Density 0.000%

    No Known Activations