© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64848
    Prev
    Next
    INDEX
    Explanations

    emojis expressing sentiment

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

    The neuron is primarily triggered by standalone emoji or emoticon characters.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    -2.45
     on
    -2.34
     at
    -2.22
     in
    -2.08
     by
    -2.03
     an
    -1.91
     all
    -1.91
     three
    -1.79
     out
    -1.79
     two
    -1.75
    POSITIVE LOGITS
     camiones
    2.25
    鹩
    2.16
     soportes
    2.11
    饜
    2.11
     seraient
    2.05
    つづく
    2.03
     voient
    2.02
     tiennent
    1.98
     siè
    1.95
    久し
    1.93
    Activations Density 0.002%

    No Known Activations