© 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. 10-GEMMASCOPE-RES-131K
    7. 103621
    Prev
    Next
    INDEX
    Explanations

    legacy and associated contexts

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

    The neuron is keyed to spotting the token “legacy.”

    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
    廰
    -3.00
    泚
    -2.67
    嫑
    -2.66
    戽
    -2.53
    熥
    -2.50
    
    -2.44
    怱
    -2.44
     are
    -2.36
    妧
    -2.31
     judíos
    -2.28
    POSITIVE LOGITS
    ’，
    2.91
    ’
    2.88
    e
    2.75
    ↵
    2.66
    as
    2.58
    f
    2.34
    !!!!
    2.27
    꽤
    2.23
    !!!!!
    2.23
    d
    2.20
    Activations Density 0.004%

    No Known Activations