© 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. 10-GEMMASCOPE-RES-131K
    4. 48034
    Prev
    Next
    INDEX
    Explanations

    import paths

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

    The neuron fires on module specifier strings in import statements—i.e. the quoted path segments (especially relative paths) following “from.”

    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
     on
    -1.44
     but
    -1.40
     for
    -1.30
     during
    -1.27
     use
    -1.27
     entonces
    -1.26
     only
    -1.24
    墮
    -1.24
     not
    -1.20
     need
    -1.20
    POSITIVE LOGITS
    different
    1.50
    loten
    1.43
     شروع
    1.42
     menyen
    1.41
     différents
    1.41
     annet
    1.39
     bensin
    1.37
    
    1.34
    sieren
    1.34
     deſt
    1.34
    Activations Density 0.089%

    No Known Activations