© 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. 40780
    Prev
    Next
    INDEX
    Explanations

    Spanish nationalities and related contexts

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

    The neuron fires strongly on occurrences of the word “Spanish” (or its substrings/derivatives) indicating references to the Spanish language or nationality.

    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
     
    -2.75
    '
    -2.48
    在场
    -2.47
     素描
    -2.36
    峮
    -2.30
    🕮
    -2.25
    をしていた
    -2.25
    
    -2.22
    の中の
    -2.19
     görüntüleri
    -2.17
    POSITIVE LOGITS
    e
    2.97
    5
    2.67
    in
    2.64
    2
    2.63
    </i>
    2.59
    3
    2.55
    1
    2.53
    In
    2.50
    m
    2.44
    b
    2.44
    Activations Density 0.014%

    No Known Activations