© 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. 92385
    Prev
    Next
    INDEX
    Explanations

    multilingual phrases and words

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

    The neuron is looking for escape‐sequence backslashes (e.g. “\n” markers) in code or markup 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
     in
    -1.06
     all
    -1.06
     M
    -1.05
    饅
    -1.05
     This
    -1.05
     Obviously
    -1.04
     what
    -1.02
     Although
    -1.02
     even
    -0.98
     by
    -0.96
    POSITIVE LOGITS
    ↵↵
    1.73
     nieuwe
    1.39
     betere
    1.10
     病院
    1.10
     unequiv
    1.09
    Här
    1.07
    werkstatt
    1.05
    ఙ
    1.05
    苼
    1.02
     工房
    1.02
    Activations Density 0.021%

    No Known Activations