© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59758
    Prev
    Next
    INDEX
    Explanations

    old-fashioned and american things

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

    The neuron fires on occurrences of “fashioned” (especially in “old-fashioned” or similar compound forms).

    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
    鱚
    -2.52
    赑
    -2.36
     موب
    -2.22
    鬭
    -2.22
    ギュア
    -2.20
    鉿
    -2.20
    ⼥
    -2.19
     puentes
    -2.16
    毉
    -2.16
     juft
    -2.13
    POSITIVE LOGITS
    ”,
    3.23
    “
    2.69
    '
    2.63
    ↵
    2.53
     —
    2.27
    lossians
    2.20
    vantaged
    2.17
     “
    2.09
    fashioned
    2.08
    —“
    2.08
    Activations Density 0.003%

    No Known Activations