© 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. 34-GEMMASCOPE-RES-131K
    4. 59171
    Prev
    Next
    INDEX
    Explanations

    develop and development

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

    words related to software development or programming across different languages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on any form of the “develop/velopment” root (e.g. develop, development, desenvolvendo, ontwikkel, etc.), i.e. tokens indicating “develop” in various languages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    truct
    -0.79
     væ
    -0.77
     النص
    -0.74
    grim
    -0.74
    liday
    -0.72
    indole
    -0.72
     mary
    -0.71
     pips
    -0.71
    chery
    -0.70
    pip
    -0.70
    POSITIVE LOGITS
     developed
    1.33
     developing
    1.16
     develop
    1.15
    ment
    1.11
     underdeveloped
    1.05
     DEVELOP
    1.03
    DEVELOP
    1.02
     developments
    1.01
     Develop
    0.97
     development
    0.97
    Activations Density 0.027%

    No Known Activations