© 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. 40681
    Prev
    Next
    INDEX
    Explanations

    controller class definition

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

    The neuron fires on Rails controller class declarations (e.g. the “class XController < ApplicationController” and related namespace 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_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
     некоторые
    -1.62
    轳
    -1.59
     некоторы
    -1.52
     triko
    -1.51
     leichte
    -1.50
    attutto
    -1.48
     inspirasi
    -1.47
    ⚢
    -1.44
     bessere
    -1.43
    /−
    -1.43
    POSITIVE LOGITS
     then
    1.48
     
    1.27
    lenen
    1.25
     attempting
    1.24
    ción
    1.23
     Viel
    1.19
     by
    1.15
    华人
    1.13
     could
    1.13
     so
    1.13
    Activations Density 0.011%

    No Known Activations