© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113353
    Prev
    Next
    INDEX
    Explanations

    HTTP methods POST, PUT, PATCH, DELETE

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

    HTTP method declarations, particularly PUT, POST, and PATCH in API/web framework code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on HTTP request method keywords (e.g. POST, PUT, PATCH) in code.

    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
     peque
    -1.45
     ''
    -1.44
     mediocre
    -1.40
     kısa
    -1.39
     cuatro
    -1.38
     competi
    -1.38
     specif
    -1.37
     ‘‘
    -1.37
     немец
    -1.36
    ⟣
    -1.35
    POSITIVE LOGITS
    there
    2.11
     this
    2.00
    Does
    1.65
    鯓
    1.57
     prata
    1.54
    ၞ
    1.53
    𓆜
    1.52
    Following
    1.52
     Surprisingly
    1.51
         
    1.49
    Activations Density 0.002%

    No Known Activations