© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19694
    Prev
    Next
    INDEX
    Explanations

    court cases, legal documents

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

    The neuron responds to long runs of leading whitespace (i.e. indentation) at the start of lines. It’s effectively detecting how far text is indented.

    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
    アメリカの
    -1.38
    大人気
    -1.21
    イタリア
    -1.19
     formação
    -1.18
     seperate
    -1.14
    人気の
    -1.13
    毎年
    -1.13
    閉店
    -1.12
    Grazie
    -1.12
     対策
    -1.10
    POSITIVE LOGITS
     It
    1.59
     

    1.53
    |')
    1.46
    ISTICS
    1.45
     herausgegeben
    1.39
     The
    1.35
    “,
    1.29
     nó
    1.29
        
    1.28
                    
    1.27
    Activations Density 0.257%

    No Known Activations