© 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. 10-GEMMASCOPE-RES-131K
    7. 11346
    Prev
    Next
    INDEX
    Explanations

    initialisms and abbreviations

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

    hexadecimal byte values in code or data structures.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron strongly activates on numeric literal tokens—especially hexadecimal numbers (e.g. “0x00…”)—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_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
    they
    -1.63
    戋
    -1.52
    They
    -1.46
    ましたが
    -1.41
    必要があります
    -1.41
    can
    -1.37
    把你
    -1.36
    幸好
    -1.36
    把她
    -1.35
    に戻る
    -1.34
    POSITIVE LOGITS
     also
    1.44
     많은
    1.38
     教室
    1.34
    촉
    1.32
     natürlich
    1.32
    asyonu
    1.32
     disciplinas
    1.27
    ”、“
    1.27
    ”，
    1.26
    ordnungen
    1.24
    Activations Density 0.000%

    No Known Activations