© 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. 10-GEMMASCOPE-RES-131K
    7. 21331
    Prev
    Next
    INDEX
    Explanations

    Makefile and LoggerFactory

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

    The neuron fires strongly on identifier names ending in “Factory” (e.g. LoggerFactory, BuilderFactory).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    После
    -2.45
    珦
    -2.34
     divisive
    -2.28
    According
    -2.28
    Despite
    -2.25
    Одна
    -2.23
    Благодаря
    -2.20
    ܜ
    -2.20
    Даже
    -2.20
    Согласно
    -2.20
    POSITIVE LOGITS
    s
    2.48
    ῞
    2.27
    に来
    2.23
    ⏑
    2.20
    前面的
    2.20
    我还是
    2.11
    <bos>
    2.09
    齜
    2.05
     following
    2.02
    就没有
    2.02
    Activations Density 0.001%

    No Known Activations