© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130205
    Prev
    Next
    INDEX
    Explanations

    The neuron activates strongly on programming identifiers (method and attribute names) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    setting recorder or UI element states

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     not
    -1.58
     two
    -1.52
     both
    -1.45
     at
    -1.42
     all
    -1.41
     their
    -1.35
     people
    -1.35
     first
    -1.30
     most
    -1.29
     as
    -1.28
    POSITIVE LOGITS
     ‌
    1.22
     WIL
    1.07
     inconsciente
    1.05
     ausein
    1.05
     někter
    1.05
     AVAILABLE
    1.05
     inapropiados
    1.04
     。
    1.02
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.00
     KR
    1.00
    Activations Density 0.016%

    No Known Activations