© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82281
    Prev
    Next
    INDEX
    Explanations

    gateway or pathway

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

    The neuron detects names of pathways, gateways, or physical access points.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     الفلسطينية
    -1.09
    歘
    -0.96
     viste
    -0.90
    Privatpatient
    -0.89
     placés
    -0.88
     acco
    -0.88
     akti
    -0.88
    Raum
    -0.87
     credo
    -0.86
     james
    -0.85
    POSITIVE LOGITS
    ed
    0.99
    yyyy
    0.95
    yy
    0.93
    farer
    0.93
    が好き
    0.92
    ibos
    0.87
    fficacy
    0.85
     caliber
    0.85
    inelli
    0.85
    theta
    0.83
    Activations Density 0.022%

    No Known Activations