© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27083
    Prev
    Next
    INDEX
    Explanations

    emotions and states

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

    The neuron is keyed to instances of the verb “feel” expressing a subjective or emotional state.

    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
     χρήση
    -2.58
    有着
    -2.39
    s
    -2.22
    fgaben
    -2.20
    m
    -2.19
    usstsein
    -2.19
     powerhouse
    -2.13
     unimaginable
    -2.08
     點
    -2.08
     quei
    -2.08
    POSITIVE LOGITS
    “
    2.63
    $
    2.05
     chrétiens
    2.05
    .“
    2.02
    ون
    1.93
    𓆝
    1.92
    ка
    1.91
    weakSelf
    1.89
    gunakan
    1.87
     ſever
    1.83
    Activations Density 0.014%

    No Known Activations