© 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. 89889
    Prev
    Next
    INDEX
    Explanations

    commentary and code delimiters

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

    The neuron is looking for numeric tokens (multi‐digit numbers) in the text.

    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
    利
    -1.11
    --.
    -1.10
    "--
    -1.10
    )--
    -1.06
    ⤒
    -1.00
    –)
    -0.98
     européennes
    -0.96
    兩
    -0.95
    
    -0.95
    --,
    -0.95
    POSITIVE LOGITS
     disconcer
    1.22
    他现在
    1.18
     intrinsically
    1.18
     approaches
    1.13
     deceiving
    1.12
     inherently
    1.08
     enlightening
    1.07
    けれ
    1.07
    他又
    1.06
     conventionally
    1.05
    Activations Density 5.845%

    No Known Activations