© 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. 34-GEMMASCOPE-RES-131K
    7. 32394
    Prev
    Next
    INDEX
    Explanations

    Arabic and Pashto names

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

    This neuron detects chunks of non-Latin script text labeled by a language tag (e.g. “Urdu:” followed by Arabic-script 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_34/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
     only
    -1.20
     first
    -1.05
     both
    -1.04
    ්
    -0.99
     could
    -0.96
     continual
    -0.95
     might
    -0.95
     nearly
    -0.93
    دان
    -0.91
     strives
    -0.90
    POSITIVE LOGITS
     delectable
    1.16
    ulitis
    1.15
     mein
    1.07
     joyous
    1.06
     horrid
    1.04
    haden
    1.04
     joi
    1.03
     luscious
    1.02
     horrifying
    1.02
     startling
    1.02
    Activations Density 0.002%

    No Known Activations