© 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. 45624
    Prev
    Next
    INDEX
    Explanations

    code punctuation; programming syntax

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

    The neuron fires on numeric literal tokens (integer numbers) in the 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
    ,
    -1.24
    &#
    -1.07
    led
    -1.05
    ]
    -1.05
    ak
    -1.01
     Hi
    -1.01
    p
    -0.97
    med
    -0.97
    ua
    -0.95
    at
    -0.95
    POSITIVE LOGITS
    Groeten
    1.09
    Politik
    1.08
    Ende
    1.05
    Legende
    1.01
    􀂃
    0.98
    ！(
    0.98
     всегда
    0.98
    ❢
    0.98
    crits
    0.96
    lyser
    0.96
    Activations Density 0.060%

    No Known Activations