© 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. 22-GEMMASCOPE-RES-131K
    7. 54297
    Prev
    Next
    INDEX
    Explanations

    diverse list items

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

    The neuron flags formal, definitional or generalizing academic phrases (e.g. “in all its forms,” “X is a Y,” “its abstract nature,” 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_22/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
    снов
    -0.94
     then
    -0.92
     stell
    -0.85
    addSubview
    -0.83
     confidential
    -0.81
    Արտաքին
    -0.78
     знать
    -0.77
     provide
    -0.76
    herokuapp
    -0.76
     Then
    -0.75
    POSITIVE LOGITS
     EVERYTHING
    1.13
    これは
    1.04
    色々な
    1.01
     étui
    1.00
    puestas
    1.00
     både
    0.99
    いろいろな
    0.98
     esportes
    0.97
     everything
    0.97
     passende
    0.96
    Activations Density 0.075%

    No Known Activations