© 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. 104392
    Prev
    Next
    INDEX
    Explanations

    damn or darn

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

    The neuron strongly detects the intensifier “damn.”

    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
     และ
    -3.31
    ୈ
    -2.95
    IZACIÓN
    -2.95
    摃
    -2.92
    噥
    -2.92
    戩
    -2.92
    噲
    -2.92
    驺
    -2.88
     แต่
    -2.81
     всѣ
    -2.81
    POSITIVE LOGITS
    '
    3.28
    ↵↵
    2.92
    ↵
    2.61
    T
    2.56
     
    2.53
    E
    2.45
    );
    2.28
    \
    2.17
    .,
    2.14
    *,
    2.13
    Activations Density 0.005%

    No Known Activations