© 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. 130644
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on iteration-related function or method names (e.g. enumerate, items, pairs, zip).

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

    enumerate items

    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
     отличи
    -1.34
    »;
    -1.29
     огня
    -1.26
    derdag
    -1.22
    侑
    -1.21
    DeleteBehavior
    -1.16
     kterou
    -1.16
     beeind
    -1.15
     varme
    -1.13
    agonal
    -1.13
    POSITIVE LOGITS
     of
    1.94
     Then
    1.43
    ↵
    1.27
    感じです
    1.25
     optimizar
    1.24
     genç
    1.21
     confines
    1.20
     seiner
    1.17
     тогда
    1.16
     município
    1.16
    Activations Density 0.000%

    No Known Activations