© 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. 22-GEMMASCOPE-RES-131K
    7. 9737
    Prev
    Next
    INDEX
    Explanations

    last names

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

    The neuron fires on capitalized family names (last names) of people.

    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
     its
    -1.70
    にします
    -1.59
    為に
    -1.51
     particular
    -1.47
    様な
    -1.45
    ところに
    -1.41
     particularly
    -1.39
    の方に
    -1.35
    を目指す
    -1.35
    感じで
    -1.34
    POSITIVE LOGITS
    を
    1.81
    が
    1.61
     who
    1.52
    <bos>
    1.51
    などを
    1.39
    などが
    1.39
    參考文獻
    1.37
    もある
    1.34
    は
    1.31
     Jr
    1.28
    Activations Density 0.039%

    No Known Activations