© 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. 36461
    Prev
    Next
    INDEX
    Explanations

    technical terms and code snippets

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

    The neuron specializes in spotting programming‐language keywords that introduce or declare code (e.g. import, class, function).

    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
    
    -1.31
     fiscale
    -1.21
     mentale
    -1.20
    ׇ
    -1.18
    录取
    -1.16
     benzin
    -1.14
     meub
    -1.13
    īb
    -1.13
     витами
    -1.11
    closedir
    -1.09
    POSITIVE LOGITS
     musíte
    1.35
    וּ
    1.33
    ־ה
    1.26
     seçenek
    1.23
     then
    1.20
    ENODEV
    1.19
     powietrza
    1.18
     będ
    1.18
    𝒙
    1.16
    pushd
    1.15
    Activations Density 0.052%

    No Known Activations