© 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. 76880
    Prev
    Next
    INDEX
    Explanations

    Provider widget configuration

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

    This neuron primarily fires on numeric tokens (digits, version numbers, regex components) and single‐quote characters (e.g. apostrophes in contractions or code).

    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
     by
    -0.81
    娑
    -0.80
     when
    -0.80
    closeConnection
    -0.78
    treeNode
    -0.77
    toThrow
    -0.77
    CTest
    -0.75
    Serum
    -0.74
    estacks
    -0.74
    дей
    -0.74
    POSITIVE LOGITS
     Provider
    1.07
    Provider
    1.05
    widget
    0.96
    provider
    0.93
     widget
    0.91
    Providers
    0.88
    ített
    0.85
    Database
    0.85
     _
    0.85
    Constants
    0.82
    Activations Density 0.001%

    No Known Activations