© 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. 10-GEMMASCOPE-RES-131K
    7. 73803
    Prev
    Next
    INDEX
    Explanations

    abbreviations and initialisms

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

    The neuron fires strongly on uppercase abbreviations or acronyms (strings of capital letters).

    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
     There
    -2.72
    $,
    -2.39
    ,
    -2.39
     可以
    -2.38
     有
    -2.36
     Если
    -2.36
     However
    -2.33
    .“
    -2.33
     Most
    -2.30
     Verhalten
    -2.30
    POSITIVE LOGITS
    锨
    2.86
    諼
    2.69
    튿
    2.47
    垟
    2.41
    not
    2.39
    盦
    2.28
    ll
    2.27
    浿
    2.25
    槩
    2.25
    に来
    2.23
    Activations Density 0.033%

    No Known Activations