© 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. 90357
    Prev
    Next
    INDEX
    Explanations

    partner or partnering with

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

    This neuron identifies occurrences of the capitalized word “Partner,” especially in code or data‐field contexts.

    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
    </strong>
    -2.20
    猡
    -2.17
     “
    -2.16
     \
    -2.09
    ”;
    -2.03
     компания
    -2.03
    🪆
    -2.03
    ”
    -2.00
    搆
    -2.00
    s
    -1.96
    POSITIVE LOGITS
    ſelf
    2.66
    what
    2.58
    Most
    2.36
    In
    2.28
    Because
    2.25
    Initially
    2.25
    最初の
    2.23
    를
    2.17
    Each
    2.17
    Like
    2.16
    Activations Density 0.004%

    No Known Activations