© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67247
    Prev
    Next
    INDEX
    Explanations

    case captions and legal filings

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

    The neuron strongly fires on long spans of whitespace or indentation (i.e. extended runs of spaces or tabs).

    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
    ية
    -2.92
    นี้
    -2.72
    𖤣
    -2.63
    ться
    -2.61
    でも
    -2.61
    
    -2.58
    ه
    -2.50
    孓
    -2.47
    ﺐ
    -2.47
    ндарт
    -2.47
    POSITIVE LOGITS
    1
    4.31
    '
    4.25
    a
    3.33
    3
    2.91
    T
    2.86
     "
    2.77
    4
    2.72
    ?”
    2.70
    s
    2.45
     
    2.42
    Activations Density 0.006%

    No Known Activations