© 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. 34-GEMMASCOPE-RES-131K
    7. 31821
    Prev
    Next
    INDEX
    Explanations

    models and modeling

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

    The neuron fires on domain‐specific technical terms—especially capitalized jargon and acronyms used in engineering or scientific contexts.

    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
     berichten
    -0.83
    に対して
    -0.77
     Verfahren
    -0.76
    rosen
    -0.75
    histogram
    -0.73
    toJson
    -0.73
    ໆ
    -0.72
    μαν
    -0.72
    指示
    -0.71
     produktów
    -0.71
    POSITIVE LOGITS
     modeling
    2.52
     modelling
    2.41
     models
    2.38
     model
    2.34
     Modeling
    2.13
    Modeling
    1.94
     Modelling
    1.94
     modeled
    1.81
    models
    1.76
    model
    1.74
    Activations Density 0.041%

    No Known Activations