© 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. 22-GEMMASCOPE-RES-131K
    7. 365
    Prev
    Next
    INDEX
    Explanations

    feeling lost or sad

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

    The neuron activates on words expressing negative emotional states or distress (e.g. “gutted,” “bummed,” “sad,” “upset,” “grief”).

    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
    叆
    -0.93
    癞
    -0.92
     frambo
    -0.92
    鸵
    -0.90
     ural
    -0.88
    izzare
    -0.88
     unsuspecting
    -0.87
    檩
    -0.86
    Iw
    -0.85
     Segen
    -0.85
    POSITIVE LOGITS
     loss
    1.60
     lost
    1.59
     missed
    1.48
     losing
    1.24
     missing
    1.24
     losses
    1.21
     नहीं
    1.20
     miss
    1.18
     lose
    1.13
     unable
    1.13
    Activations Density 0.032%

    No Known Activations