© 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. 10-GEMMASCOPE-RES-131K
    7. 11737
    Prev
    Next
    INDEX
    Explanations

    html `>`

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

    the opening brace of an enumeration or code block, particularly in programming language syntax.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on code literal “null.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     personlig
    -1.86
     tidligere
    -1.70
     this
    -1.69
     enkelte
    -1.57
     tromper
    -1.55
     olimp
    -1.54
     senere
    -1.53
    훌
    -1.52
     visst
    -1.51
    接过
    -1.50
    POSITIVE LOGITS
     '
    1.65
     unimp
    1.38
    不但
    1.38
    怎麼
    1.37
    :
    1.32
    不仅
    1.30
    0
    1.29
     não
    1.28
     не
    1.28
    ]
    1.27
    Activations Density 0.001%

    No Known Activations