© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 60324
    Prev
    Next
    INDEX
    Explanations

    code components

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

    The neuron peaks on PHP namespace and class name segments (PascalCase identifiers) in fully qualified class paths.

    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
     étan
    -1.88
    !’
    -1.55
     inappropri
    -1.48
    
    -1.45
    みたいな
    -1.43
     Didn
    -1.42
     дополнительных
    -1.41
    
    -1.41
     serão
    -1.37
     afirmou
    -1.37
    POSITIVE LOGITS
     of
    1.88
     as
    1.83
     for
    1.70
     to
    1.61
     catalog
    1.53
    ruguay
    1.53
     with
    1.51
     without
    1.46
     at
    1.39
     while
    1.35
    Activations Density 0.011%

    No Known Activations