© 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. 98196
    Prev
    Next
    INDEX
    Explanations

    Unfortunately, code, and other languages

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

    The neuron flags numeric literals (constants) 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_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
     that
    -1.30
    ఝ
    -1.10
     nabízí
    -1.09
     atletas
    -1.08
     wrze
    -1.07
     herencia
    -1.03
     tillegg
    -1.03
     unión
    -1.02
    ௌ
    -1.01
     oposición
    -1.00
    POSITIVE LOGITS
     even
    0.96
    というわけで
    0.93
     даже
    0.91
     is
    0.89
    лят
    0.88
    ｒ
    0.88
    ねー
    0.86
     समस्या
    0.86
     by
    0.85
     フラット
    0.85
    Activations Density 0.001%

    No Known Activations