© 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. 68404
    Prev
    Next
    INDEX
    Explanations

    programming language concepts

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

    The neuron fires on CamelCase (or PascalCase) identifier tokens (e.g. romanToInt, nextGreaterElements, LeetCode problem URLs).

    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
    ContentAlignment
    -1.08
    舛
    -1.08
    数十
    -1.05
    leeve
    -1.04
    ----</
    -1.03
    DrawerToggle
    -1.03
     peuple
    -1.02
    纜
    -1.02
    리가
    -1.02
    prech
    -1.01
    POSITIVE LOGITS
     американ
    1.37
     США
    1.20
     häufig
    1.11
    𝑰
    1.05
     US
    1.02
    ReturnType
    1.00
     such
    0.98
    GORITHM
    0.96
     American
    0.96
     maniere
    0.96
    Activations Density 0.018%

    No Known Activations