© 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. 81126
    Prev
    Next
    INDEX
    Explanations

    code syntax punctuation

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

    The neuron fires on code identifiers—names of classes, modules, methods, properties, or constants in source code.

    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
     ہے
    -1.47
     and
    -1.40
     this
    -1.37
    </h2>
    -1.37
     when
    -1.35
    )
    -1.34
     the
    -1.32
     its
    -1.30
    ↵↵
    -1.28
    lacoste
    -1.28
    POSITIVE LOGITS
    ().
    2.91
    .
    2.33
    '].
    2.20
    }$.
    2.08
    $.
    2.03
    «.
    1.99
    "].
    1.98
    *.
    1.98
    [].
    1.89
    。
    1.88
    Activations Density 0.042%

    No Known Activations