© 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. 66258
    Prev
    Next
    INDEX
    Explanations

    U.S

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

    The neuron strongly activates on occurrences of the U.S. country abbreviation (“U.S.”).

    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
    ículos
    -1.98
    に来て
    -1.72
    ệc
    -1.72
    廔
    -1.63
    に行ってきました
    -1.59
    薅
    -1.53
    苼
    -1.52
    更大的
    -1.51
    今月
    -1.51
     that
    -1.49
    POSITIVE LOGITS
    "
    1.91
    '
    1.66
     ''
    1.50
     ребенку
    1.49
    ''
    1.47
    O
    1.46
     morgens
    1.42
    -
    1.38
    an
    1.37
     ventes
    1.37
    Activations Density 0.020%

    No Known Activations