© 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. 10263
    Prev
    Next
    INDEX
    Explanations

    seriously followed by adjective or verb

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

    The neuron specifically fires on occurrences of the adverb “seriously.”

    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
    为大家
    -2.56
     disheart
    -2.55
    谖
    -2.45
    𖣔
    -2.42
     hangout
    -2.42
    ти
    -2.39
    ЛИ
    -2.36
    ㉕
    -2.34
    接着
    -2.31
    皷
    -2.30
    POSITIVE LOGITS
    '
    3.41
    .
    3.39
     که
    2.53
    0
    2.52
     возможность
    2.45
    a
    2.45
    the
    2.28
    that
    2.27
    的问道
    2.23
    s
    2.19
    Activations Density 0.007%

    No Known Activations