© 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. 25918
    Prev
    Next
    INDEX
    Explanations

    code identifiers and punctuation

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

    The neuron activates on numeric literals and non‐alphabetic symbols (e.g. digits and punctuation) commonly found in code or math expressions.

    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
    אם
    -1.09
     長袖
    -1.08
    vestido
    -1.05
    Tidak
    -1.04
    Egypte
    -1.03
    Tujuan
    -1.03
     laced
    -1.02
    mamış
    -1.01
     или
    -1.00
    Você
    -1.00
    POSITIVE LOGITS
     only
    1.42
    </h3>
    1.09
     other
    1.07
    </h4>
    0.98
    </h2>
    0.95
    lages
    0.93
    医药
    0.92
    回了
    0.91
     also
    0.91
    県の
    0.90
    Activations Density 0.174%

    No Known Activations