© 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. 70433
    Prev
    Next
    INDEX
    Explanations

    acronyms and emotional contexts

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

    The neuron responds to short tokens written as all-caps abbreviations or acronyms.

    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
    縢
    -3.61
     It
    -2.86
     utilizzando
    -2.50
    鵟
    -2.27
    ين
    -2.22
    GIVEREF
    -2.20
    魮
    -2.20
    踯
    -2.14
     we
    -2.13
    黉
    -2.13
    POSITIVE LOGITS
     самых
    2.36
    *
    2.31
     лучших
    2.19
    b
    2.14
    F
    2.13
    ve
    2.11
     särsk
    2.09
    鏖
    2.08
     duros
    2.03
     ESG
    2.00
    Activations Density 0.001%

    No Known Activations