© 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. 71398
    Prev
    Next
    INDEX
    Explanations

    function exits

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

    This neuron flags domain-specific technical terms—especially programming API identifiers (e.g. class or method names) and specialized scientific/medical jargon.

    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
     både
    -1.15
     eſt
    -1.15
    
    -1.13
     tatou
    -1.13
     ſever
    -1.13
     applau
    -1.13
     patienter
    -1.10
     élev
    -1.09
     uſ
    -1.09
     spesifik
    -1.09
    POSITIVE LOGITS
     $
    1.19
     —
    1.17
     newly
    1.10
     ”
    1.09
     helps
    1.05
     information
    1.05
     out
    1.03
     re
    1.02
     new
    1.02
     go
    1.01
    Activations Density 0.199%

    No Known Activations