© 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. 42677
    Prev
    Next
    INDEX
    Explanations

    Dorset and Lorenzo Parodi

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

    The neuron detects mentions of the place name “Dorset.”

    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
    medriver
    -2.19
     kategori
    -2.11
     pittores
    -2.02
     châ
    -2.00
     camiset
    -1.98
     收納
    -1.98
     mereka
    -1.97
     struk
    -1.96
     ruh
    -1.95
     seks
    -1.94
    POSITIVE LOGITS
     lepiej
    2.19
    她
    2.14
    ?’
    2.13
    허
    2.09
    $
    2.06
    这里
    2.05
    si
    2.05
    ).
    1.98
     lepší
    1.97
     długo
    1.96
    Activations Density 0.000%

    No Known Activations