© 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. 22-GEMMASCOPE-RES-131K
    7. 14513
    Prev
    Next
    INDEX
    Explanations

    file paths and code snippets

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

    The neuron strongly activates on forward‐slash separators and adjoining directory or file names (i.e. UNIX‐style file‐path tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     so
    -1.28
     of
    -1.26
     through
    -1.21
     for
    -1.13
     indicating
    -1.10
     melalui
    -1.02
     what
    -0.98
     disini
    -0.96
     July
    -0.94
    いただけます
    -0.94
    POSITIVE LOGITS
     getestet
    1.22
    specifically
    1.20
    mainly
    1.20
    鵙
    1.18
     хорошее
    1.13
     Oswego
    1.11
    andaag
    1.10
    mostly
    1.06
     entraî
    1.06
     onde
    1.06
    Activations Density 0.002%

    No Known Activations