© 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. 99644
    Prev
    Next
    INDEX
    Explanations

    Malaysia and Malaysian references

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

    The neuron fires strongly on structural “label” tokens—e.g. infobox fields (Town, Malaysia), section-heading words (Opening, time), and boilerplate abstract intros (“the aims of this study”)—rather than on ordinary running 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
    izumi
    -0.82
     sudah
    -0.79
     bereits
    -0.79
    mayr
    -0.77
    dorp
    -0.73
     альтерна
    -0.72
     から
    -0.72
    فوائد
    -0.69
     več
    -0.69
     melalui
    -0.68
    POSITIVE LOGITS
    Longrightarrow
    0.87
    ситет
    0.82
    Faculty
    0.81
     AssemblyProduct
    0.81
    ülés
    0.77
     आइटम
    0.76
     Faculty
    0.76
     Moors
    0.74
     преподава
    0.74
     Cube
    0.74
    Activations Density 0.004%

    No Known Activations