© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 53960
    Prev
    Next
    INDEX
    Explanations

    HTTP POST requests

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

    The neuron is primarily activated by numeric tokens (multi‐digit numbers, numeric literals, and digit‐containing symbols) in code or command 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_34/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
     getters
    -0.82
     getter
    -0.81
    getter
    -0.76
     اكتوبر
    -0.75
     &(
    -0.70
    onRequest
    -0.70
    GetMapping
    -0.70
    neu
    -0.68
    ENTIAL
    -0.68
     clustering
    -0.68
    POSITIVE LOGITS
     POST
    4.25
     post
    4.03
    POST
    3.94
    post
    3.48
    Post
    3.34
     Post
    3.33
     posting
    2.72
    HttpPost
    2.56
     posts
    2.53
     пост
    2.52
    Activations Density 0.123%

    No Known Activations