© 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. 39287
    Prev
    Next
    INDEX
    Explanations

    describing firms and their actions

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

    The neuron is tuned to detect mentions of a business entity (for example, the word “firm”).

    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
    媗
    -2.67
    ↵
    -2.23
     immense
    -2.05
    ᥬ
    -2.03
     Our
    -2.03
     sabores
    -2.02
    
    -2.02
     We
    -2.00
     чёр
    -1.99
     ſame
    -1.96
    POSITIVE LOGITS
    k
    2.69
    o
    2.44
    E
    2.39
    mathrm
    2.34
    can
    2.31
    I
    2.31
    st
    2.30
    ta
    2.22
    h
    2.19
    r
    2.16
    Activations Density 0.008%

    No Known Activations