© 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. 34-GEMMASCOPE-RES-131K
    7. 89702
    Prev
    Next
    INDEX
    Explanations

    scheduling software and apps

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

    The neuron is sensitive to long alphanumeric or technical identifiers—things like domain names/URLs, file paths, product or company names, acronyms, and standalone numbers.

    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
    proposition
    -0.82
    ämie
    -0.77
    Explor
    -0.74
     tweeter
    -0.73
     Skype
    -0.72
    ائية
    -0.72
     murmured
    -0.71
    skype
    -0.71
    torta
    -0.71
    هرست
    -0.70
    POSITIVE LOGITS
     software
    1.93
     Software
    1.69
    Software
    1.55
    software
    1.55
    软件
    1.31
     softwares
    1.27
     SOFTWARE
    1.23
    SOFTWARE
    1.20
     logiciel
    1.19
     scheduling
    1.14
    Activations Density 0.046%

    No Known Activations