© 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. 98401
    Prev
    Next
    INDEX
    Explanations

    code snippets

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

    The neuron fires most on code identifiers that include uppercase letters (e.g. CamelCase or ALL-CAP names).

    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
     those
    -1.25
     many
    -1.02
    Those
    -1.01
     most
    -1.00
     numerous
    -0.99
     only
    -0.98
     more
    -0.97
     mostly
    -0.93
     additional
    -0.92
    อยู่ใน
    -0.91
    POSITIVE LOGITS
     bevol
    0.90
     grunge
    0.90
     gebou
    0.87
     propietarios
    0.85
     completar
    0.83
     !!!!
    0.83
    不好的
    0.82
     senza
    0.82
     abſ
    0.81
     את
    0.81
    Activations Density 0.025%

    No Known Activations