© 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. 87340
    Prev
    Next
    INDEX
    Explanations

    IO abbreviations, acronyms

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

    This neuron activates on short all‐caps letter sequences (acronyms/initialisms) in the text.

    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
     NEVER
    -2.63
     There
    -2.56
     Why
    -2.55
     Giving
    -2.55
    </h5>
    -2.52
     از
    -2.31
     Following
    -2.30
     Surprisingly
    -2.30
     Very
    -2.28
     After
    -2.23
    POSITIVE LOGITS
    </strong>
    3.34
    鹇
    3.27
    鲧
    3.16
    廰
    2.92
    糨
    2.81
    猻
    2.70
    釤
    2.70
     harten
    2.56
    ౧
    2.52
    锨
    2.52
    Activations Density 0.002%

    No Known Activations