© 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. 99387
    Prev
    Next
    INDEX
    Explanations

    Bangladesh and Bengali context

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

    the presence of numeric date tokens (especially four-digit years) in historical context

    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
     np
    -0.77
    PINES
    -0.77
     са
    -0.75
    below
    -0.74
     ступен
    -0.71
     Pen
    -0.71
     vu
    -0.71
     pen
    -0.70
     latest
    -0.70
    gawa
    -0.70
    POSITIVE LOGITS
     Bangladesh
    1.47
    Bangladesh
    1.44
     Banglades
    1.30
     Bengali
    1.13
     Dhaka
    1.02
    East
    0.96
    ladesh
    0.96
     Beng
    0.92
    Dak
    0.92
     intellectuals
    0.90
    Activations Density 0.015%

    No Known Activations