© 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. 87251
    Prev
    Next
    INDEX
    Explanations

    company entities

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

    The neuron fires on multiword uppercase organization or institution names (e.g. insurance companies, courts, corporations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     fortal
    -0.89
     gorra
    -0.85
     Rússia
    -0.84
     índ
    -0.84
     tudi
    -0.84
     artista
    -0.84
     novela
    -0.83
     guideline
    -0.82
     ؛
    -0.81
    推出
    -0.81
    POSITIVE LOGITS
     entities
    1.24
     LLC
    1.07
     Inc
    1.02
     unicorns
    0.82
     Rohing
    0.81
    作詞
    0.81
     Muhammadu
    0.79
    参赛
    0.79
     entity
    0.78
    Entities
    0.78
    Activations Density 0.161%

    No Known Activations