© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86008
    Prev
    Next
    INDEX
    Explanations

    code file paths

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

    This neuron activates on file‐path components (directory or module names and separators) in import/require statements.

    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
     nettsted
    -1.51
    是一款
    -1.40
    
    -1.38
     spesielt
    -1.34
    LLABLE
    -1.32
    ě
    -1.31
     informasjon
    -1.27
    綺麗
    -1.26
    ered
    -1.25
    ITARY
    -1.24
    POSITIVE LOGITS
     have
    1.58
     discussions
    1.44
    expiresIn
    1.41
    Those
    1.41
     still
    1.34
     lievito
    1.30
    Our
    1.30
     "@/
    1.26
    なりに
    1.23
     should
    1.21
    Activations Density 0.010%

    No Known Activations