© 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. 105059
    Prev
    Next
    INDEX
    Explanations

    cuddle, cuddly, lick

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

    The neuron activates on words describing close, affectionate physical gatherings or embraces—cuddling, snuggling, or huddling together.

    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
    洨
    -2.02
     HONORABLE
    -2.02
    Ꮉ
    -2.02
    '
    -1.98
    ﺕ
    -1.98
     Awal
    -1.97
     Hacer
    -1.96
    ある
    -1.96
    𖥧
    -1.95
     VARIOUS
    -1.93
    POSITIVE LOGITS
    因为他
    1.98
    ’
    1.86
     perched
    1.79
    𝐒
    1.77
    atore
    1.73
     distraught
    1.72
    <i>
    1.72
     propuestas
    1.68
    也非常
    1.66
    全新的
    1.66
    Activations Density 0.006%

    No Known Activations