© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65582
    Prev
    Next
    INDEX
    Explanations

    technical identifiers and abbreviations

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

    This neuron detects tokens that are technical identifiers or acronyms—especially uppercase sequences, version numbers, or code names combining letters, digits, and punctuation.

    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
     of
    -1.17
     this
    -1.13
     the
    -0.99
    извест
    -0.94
     novios
    -0.93
     his
    -0.93
    ことも
    -0.92
    llte
    -0.90
     some
    -0.89
     their
    -0.89
    POSITIVE LOGITS
    nade
    1.07
    <bos>
    1.04
    天的
    1.01
    Câ
    1.00
    rtl
    1.00
    {-\
    0.98
    vábbi
    0.97
    がありますが
    0.93
    üte
    0.93
    もあります
    0.92
    Activations Density 0.001%

    No Known Activations