© 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. 10-GEMMASCOPE-RES-131K
    7. 42140
    Prev
    Next
    INDEX
    Explanations

    PDP, ministry, passengers, Telecom, Eskom, employment

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

    The neuron detects uppercase multi‐letter acronyms denoting organizations or government agencies.

    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
    5
    -1.27
     how
    -1.16
    pleen
    -1.09
     przechowy
    -1.09
    uterte
    -1.08
     viste
    -1.08
     stampa
    -1.08
     کرده
    -1.06
     used
    -1.05
     felpa
    -1.05
    POSITIVE LOGITS
    ]],
    1.17
     earnest
    1.10
     semuanya
    1.04
    ,
    1.02
    abilir
    1.01
    "/>
    1.01
     eenige
    0.98
    írás
    0.98
     Erst
    0.98
    надца
    0.98
    Activations Density 0.034%

    No Known Activations