© 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. 104811
    Prev
    Next
    INDEX
    Explanations

    sweet followed by nouns or phrases

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

    The neuron selectively activates on the literal token “sweet” (in any capitalization or context).

    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
     "
    -3.41
    ৄ
    -3.09
     anche
    -2.83
    ’
    -2.66
     a
    -2.66
     praktisch
    -2.64
    てん
    -2.50
     \
    -2.48
     Ähn
    -2.41
     overriding
    -2.41
    POSITIVE LOGITS
    鋮
    3.19
    that
    3.14
     That
    2.91
    Among
    2.83
     که
    2.77
    While
    2.77
    Unlike
    2.73
    Despite
    2.70
    Although
    2.69
    禇
    2.69
    Activations Density 0.004%

    No Known Activations