© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68916
    Prev
    Next
    INDEX
    Explanations

    nice, nicer, nicely

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

    The neuron activates on the word “nice” and its morphological variants (e.g. nicer, nicely).

    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
    </em>
    -1.91
     of
    -1.89
     irrespective
    -1.77
     verschill
    -1.73
    </sup>
    -1.72
    骓
    -1.72
    ৄ
    -1.71
    ༐
    -1.70
     and
    -1.69
     are
    -1.69
    POSITIVE LOGITS
    ties
    1.91
    在他的
    1.81
    Beberapa
    1.80
    ﮭ
    1.78
    Instead
    1.74
    Berdasarkan
    1.74
    ᠂
    1.74
    Kondisi
    1.73
    ﱠ
    1.73
    …」
    1.72
    Activations Density 0.007%

    No Known Activations