© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26043
    Prev
    Next
    INDEX
    Explanations

    programming data types and containers

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

    This neuron detects programming language type names (e.g. int, String, byte) in code.

    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
     уже
    -1.36
    其他
    -1.29
     if
    -1.29
     sehr
    -1.28
     internas
    -1.27
    Xna
    -1.27
     tambor
    -1.26
     altre
    -1.22
     crafted
    -1.22
     kümmern
    -1.21
    POSITIVE LOGITS
    de
    1.20
    o
    1.19
     einander
    1.18
     откри
    1.18
    no
    1.10
    &
    1.05
    心头
    1.05
    習
    1.05
     zweier
    1.05
    represented
    1.04
    Activations Density 0.001%

    No Known Activations