© 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. 10-GEMMASCOPE-RES-131K
    7. 75662
    Prev
    Next
    INDEX
    Explanations

    maven project files

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

    The neuron fires on occurrences of “maven” in XML namespace/schema declarations (i.e. in Maven POM files).

    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
    i
    -3.45
    *
    -3.03
    ]
    -2.80
    ي
    -2.50
    z
    -2.39
     After
    -2.36
     How
    -2.30
    彣
    -2.23
    e
    -2.20
    鄚
    -2.20
    POSITIVE LOGITS
    龊
    2.75
     другие
    2.61
     andere
    2.45
    lossians
    2.28
     barata
    2.28
     cliquer
    2.27
    襌
    2.22
    ᛬
    2.20
    dientemente
    2.16
    檍
    2.14
    Activations Density 0.002%

    No Known Activations