© 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. 110814
    Prev
    Next
    INDEX
    Explanations

    decision making processes

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

    The neuron responds to occurrences of the word “making,” especially as a suffix in compound terms (e.g. decision-making, rule-making).

    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
    缑
    -2.08
     planètes
    -1.97
    鑄
    -1.93
     termed
    -1.90
    鈣
    -1.88
     manières
    -1.84
     dizaines
    -1.84
     nieruch
    -1.83
    鲼
    -1.82
     élections
    -1.81
    POSITIVE LOGITS
    We
    2.42
    </sup>
    2.27
    攆
    2.23
     lessen
    2.22
    the
    2.22
    </h4>
    2.16
    ኹ
    2.16
    those
    2.13
    they
    2.11
     dilapidated
    2.11
    Activations Density 0.020%

    No Known Activations