© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27945
    Prev
    Next
    INDEX
    Explanations

    ActiveRecord `Base` `Model` classes

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

    The neuron detects class‐inheritance declarations in code (e.g. “class Xxx < Yyy::Zzz”).

    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
    SequentialGroup
    -1.16
    getClassLoader
    -1.09
     toalla
    -1.09
    ikti
    -1.07
    getSystemService
    -1.06
     satisfactor
    -1.06
     custos
    -1.05
    "):
    -1.04
     Información
    -1.03
    '],
    -1.03
    POSITIVE LOGITS
    敍
    1.08
    やる
    1.00
     ausschließlich
    0.99
    They
    0.98
     linking
    0.97
    メモリ
    0.94
     has
    0.93
    籃
    0.93
    ภัย
    0.91
    やった
    0.90
    Activations Density 0.005%

    No Known Activations