© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69723
    Prev
    Next
    INDEX
    Explanations

    NFT acronyms and related phrases

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

    The neuron responds to the repeated scientific acronym “NFT” (often followed by numbers), i.e. occurrences of that all-caps abbreviation.

    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
    1
    -4.16
    7
    -3.84
    8
    -3.20
    3
    -3.06
    6
    -3.03
    9
    -2.89
    4
    -2.86
    0
    -2.80
    2
    -2.67
     фирмы
    -2.59
    POSITIVE LOGITS
     Because
    2.42
    彇
    2.31
    𝔨
    2.22
     estratégico
    2.20
     sucedió
    2.20
     ocurrió
    2.13
    ∏
    2.13
     Umfang
    2.11
     
    2.09
    ᡴ
    2.09
    Activations Density 0.000%

    No Known Activations