© 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. 34-GEMMASCOPE-RES-131K
    7. 90254
    Prev
    Next
    INDEX
    Explanations

    string literal closing quotes

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

    The neuron fires on non‐alphanumeric code symbols and punctuation (e.g. braces, brackets, colons, question marks, operators).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     "",
    -1.73
    (),
    -1.70
     [],
    -1.60
     '',
    -1.59
    (),
    -1.55
     "-",
    -1.46
    ^{*},
    -1.42
    ++,
    -1.37
     ".",
    -1.36
    "",
    -1.35
    POSITIVE LOGITS
    "),
    1.28
    ),
    1.26
     ),
    1.15
    '),
    1.11
    .),
    1.09
    _),
    1.09
     "),
    1.09
    `),
    1.04
    ）、
    1.04
    ”),
    1.02
    Activations Density 0.145%

    No Known Activations