© 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. 124121
    Prev
    Next
    INDEX
    Explanations

    how adjective

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

    The main thing this neuron does is detect descriptive adjectives conveying evaluation or sentiment (e.g., great, terrible, common, valuable).

    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
    ſelves
    -1.86
     们
    -1.72
     arrivée
    -1.71
    骉
    -1.69
    t
    -1.65
     étendue
    -1.64
     supplémentaire
    -1.64
     вещества
    -1.63
    EdgeInsets
    -1.63
    であれば
    -1.62
    POSITIVE LOGITS
     it
    2.91
     they
    2.66
     these
    2.42
    6
    2.39
     you
    2.17
     this
    2.13
     or
    1.80
    9
    1.63
    鑁
    1.62
     namun
    1.59
    Activations Density 0.019%

    No Known Activations