© 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. 66491
    Prev
    Next
    INDEX
    Explanations

    PSP, NAC, Postgres, NSE acronyms

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

    This neuron activates on standalone uppercase acronyms or initialisms (e.g. PSP, SPD, NAC, Postgres) 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
    as
    -3.27
    ﹑
    -2.75
    with
    -2.75
     avec
    -2.67
    
    -2.63
     the
    -2.58
    nown
    -2.44
    .,
    -2.41
    戋
    -2.33
    岽
    -2.33
    POSITIVE LOGITS
    !”
    3.28
    ?”
    2.59
     divertidas
    2.56
    ※※
    2.50
    section
    2.39
    ”，
    2.33
     baratas
    2.33
    有时候
    2.25
     modernas
    2.20
     inspiradoras
    2.17
    Activations Density 0.012%

    No Known Activations