© 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. 104842
    Prev
    Next
    INDEX
    Explanations

    describing cute things

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

    The main thing this neuron does is detect adjectives expressing strong cuteness (e.g., “cute,” “adorable”).

    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
     to
    -2.08
    ’
    -1.69
    -1.68
     from
    -1.68
    the
    -1.59
    )$
    -1.57
    より
    -1.57
    up
    -1.55
     Meningkatkan
    -1.55
    ise
    -1.51
    POSITIVE LOGITS
     disdain
    1.73
     desafios
    1.68
    ⭓
    1.61
    ᨗ
    1.60
    gucci
    1.58
    起码
    1.57
    噘
    1.55
    ᠂
    1.55
     agujero
    1.54
    méno
    1.54
    Activations Density 0.009%

    No Known Activations