© 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. 75338
    Prev
    Next
    INDEX
    Explanations

    feeling sad

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

    The neuron activates on the word “sad” (and its close variants), effectively spotting expressions of sadness.

    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
     และ
    -3.02
    轳
    -2.98
    䊐
    -2.94
    蛏
    -2.91
    guigu
    -2.91
    乆
    -2.89
    錞
    -2.89
     of
    -2.89
    GETHER
    -2.88
    噲
    -2.88
    POSITIVE LOGITS
    s
    3.66
    </b>
    3.09
    that
    3.08
    )
    2.92
    or
    2.91
    似乎
    2.86
    one
    2.75
    或
    2.72
    های
    2.53
    /
    2.48
    Activations Density 0.003%

    No Known Activations