© 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. 22012
    Prev
    Next
    INDEX
    Explanations

    Begin, Client, none, Error, The, oil, I, \, micros, Organic, royal, measures

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

    quotation marks in code or technical documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is detecting occurrences of the escaped‐quote sequence `\"`.

    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
    s
    -5.03
    1
    -3.55
    i
    -3.16
    4
    -2.89
    0
    -2.80
     meisten
    -2.72
    y
    -2.69
    一些
    -2.64
    -2.61
    可以
    -2.61
    POSITIVE LOGITS
     of
    3.27
    龊
    2.98
    扪
    2.70
    場は
    2.66
    惕
    2.58
    ))}
    2.56
    見ても
    2.56
    互联网档案馆
    2.53
    珧
    2.52
    了自己
    2.39
    Activations Density 0.003%

    No Known Activations