© 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. 42762
    Prev
    Next
    INDEX
    Explanations

    company name endings

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

    The neuron fires on corporate‐entity name tokens—especially the “Co.”/“Ltd.” suffixes in company names.

    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
     by
    -1.98
    For
    -1.63
    ',
    -1.56
     but
    -1.55
    On
    -1.41
     gemeinsame
    -1.40
     It
    -1.38
    ︲
    -1.38
    ts
    -1.38
    ek
    -1.37
    POSITIVE LOGITS
    ftet
    1.60
    ateness
    1.53
     senjata
    1.52
     aventures
    1.52
     mourir
    1.51
    siguiente
    1.48
     upor
    1.45
    akses
    1.44
     areia
    1.43
     Pedido
    1.43
    Activations Density 0.013%

    No Known Activations