© 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. 34-GEMMASCOPE-RES-131K
    7. 78853
    Prev
    Next
    INDEX
    Explanations

    ForEach construct

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

    This neuron detects PowerShell cmdlet names (the verb–noun tokens like Add-, Get-, Set-, Out-, 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_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
    মান
    -0.79
    artifactId
    -0.73
    чному
    -0.72
     Kwon
    -0.72
    ೦
    -0.71
    咚
    -0.70
     Refer
    -0.69
    mpar
    -0.69
     instrumental
    -0.68
     Taschen
    -0.68
    POSITIVE LOGITS
     âgées
    0.82
    StrictMode
    0.82
     bourse
    0.77
    infor
    0.75
     बच्
    0.75
    PSS
    0.74
     Oso
    0.73
     Harts
    0.73
     Farmhouse
    0.73
     PSS
    0.72
    Activations Density 0.043%

    No Known Activations