© 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. 128521
    Prev
    Next
    INDEX
    Explanations

    cloud api and sdk

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

    The neuron fires on Azure‐related infrastructure and tooling terms (e.g. Azure, ARM, Resource Manager, CLI, SDK, template, subscription).

    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
     our
    -1.63
    a
    -1.43
    poran
    -1.38
     longtime
    -1.38
     nossos
    -1.38
     Much
    -1.38
     nossa
    -1.34
     intricate
    -1.30
     Of
    -1.30
     if
    -1.30
    POSITIVE LOGITS
    橛
    1.49
    蟶
    1.42
     núcleos
    1.42
     każdym
    1.40
     июня
    1.38
    getReal
    1.38
    خیلی
    1.37
    ſch
    1.34
    },
    1.33
    Alas
    1.33
    Activations Density 0.015%

    No Known Activations