© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33656
    Prev
    Next
    INDEX
    Explanations

    technical terms and data

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

    This neuron detects Spanish words (i.e. Spanish-language tokens) in code or comments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     OGSÅ
    -1.17
     Przed
    -1.15
     می‌توان
    -1.13
    Vaata
    -1.12
     Werken
    -1.12
     Czę
    -1.09
    banez
    -1.09
     geográfica
    -1.08
     этих
    -1.08
     cordón
    -1.06
    POSITIVE LOGITS
    ầ
    1.16
    เมื่อ
    1.07
    )
    1.04
     ögon
    1.03
    だったが
    1.02
     besö
    1.01
     säkert
    1.01
     käns
    0.99
     säl
    0.99
     lyck
    0.96
    Activations Density 0.031%

    No Known Activations