© 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. 59964
    Prev
    Next
    INDEX
    Explanations

    give Two figs

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

    The neuron fires on words that carry an emotional or attitudinal stance (e.g. sentiment-laden terms).

    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
     .”
    -1.91
     divertidas
    -1.77
    ).”
    -1.67
    鸰
    -1.56
    rosis
    -1.52
    dată
    -1.52
    culosis
    -1.49
    rogène
    -1.47
     ”
    -1.45
    ”.
    -1.45
    POSITIVE LOGITS
    :
    1.90
    入
    1.49
    訫
    1.48
     santuario
    1.45
     prochaines
    1.45
    现在的
    1.45
    眎
    1.42
    苼
    1.41
    '
    1.37
    仉
    1.34
    Activations Density 0.145%

    No Known Activations