© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71857
    Prev
    Next
    INDEX
    Explanations

    company Inc. suffix

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

    The neuron fires on the token “Inc,” i.e. the corporate incorporation suffix 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_22/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
    ts
    -2.66
    に
    -2.64
    <td>
    -2.61
    )$
    -2.39
    </td>
    -2.38
     unmittel
    -2.36
    M
    -2.31
     kinds
    -2.27
     namun
    -2.23
     kontinuier
    -2.23
    POSITIVE LOGITS
     italien
    2.19
    鱻
    2.13
    を終
    2.06
    橚
    2.05
    焿
    2.00
     Для
    1.99
    Hanya
    1.99
    ︕
    1.98
    人在
    1.98
    sandália
    1.98
    Activations Density 0.026%

    No Known Activations