© 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. 12953
    Prev
    Next
    INDEX
    Explanations

    household and associated concepts

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

    The neuron responds to occurrences of the word “household” (and its closely related forms) in the text.

    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
     "
    -2.52
     The
    -2.20
    getreten
    -2.02
    きち
    -1.94
    ↵
    -1.91
     We
    -1.91
     incontr
    -1.89
     它
    -1.89
    饪
    -1.88
     年轻
    -1.87
    POSITIVE LOGITS
    <bos>
    2.70
    to
    2.53
    狁
    2.48
     other
    2.36
     fend
    2.16
    ers
    2.14
    与此同时
    2.11
                
    2.03
    ☫
    2.02
     spanning
    1.98
    Activations Density 0.004%

    No Known Activations