© 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. 10-GEMMASCOPE-RES-131K
    7. 99072
    Prev
    Next
    INDEX
    Explanations

    Indonesian words and verbs

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

    The neuron is highly responsive to Indonesian-language tokens, effectively flagging when the text switches into Indonesian.

    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
    ]
    -2.27
    ier
    -1.94
     другим
    -1.89
     że
    -1.84
    is
    -1.79
     VERY
    -1.79
     первая
    -1.78
    ные
    -1.74
     illuminating
    -1.74
    𖤍
    -1.73
    POSITIVE LOGITS
     conftest
    2.08
    蘩
    2.06
     lname
    1.95
     Saltar
    1.93
     antena
    1.88
     tokio
    1.84
     strane
    1.81
     emporio
    1.79
     parachoque
    1.77
     SearchView
    1.76
    Activations Density 0.002%

    No Known Activations