© 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. 84858
    Prev
    Next
    INDEX
    Explanations

    tests and code snippets

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

    The neuron fires on spans of leading whitespace (indentation) at the beginnings of lines.

    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
     is
    -1.62
     (
    -1.46
    h
    -1.42
    ↵
    -1.41
     needed
    -1.41
    q
    -1.31
     есть
    -1.29
    k
    -1.25
     presents
    -1.24
     aims
    -1.24
    POSITIVE LOGITS
     from
    1.81
     sintió
    1.58
     this
    1.55
    either
    1.51
     mindig
    1.45
     like
    1.43
     either
    1.37
    
    1.34
     Either
    1.34
    がこの
    1.32
    Activations Density 0.012%

    No Known Activations