© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74807
    Prev
    Next
    INDEX
    Explanations

    JetBrains products and company

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

    The neuron detects mentions of JetBrains (and their products or namespaces), e.g. occurrences of "JetBrains," "PhpStorm," "IntelliJ IDEA," "PyCharm," etc.

    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
     "]";
    -1.67
    JKLM
    -1.60
     حتما
    -1.59
    鐠
    -1.56
    英語版
    -1.53
    ～～～～
    -1.51
    不管是
    -1.46
    大概是
    -1.46
     може
    -1.45
    dí
    -1.45
    POSITIVE LOGITS
    ’
    2.38
    .
    2.31
     are
    1.62
    ers
    1.55
    }$
    1.43
     Work
    1.36
    
    1.34
    ции
    1.34
    っとり
    1.31
    1.30
    Activations Density 0.021%
    No Known Activations