© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28116
    Prev
    Next
    INDEX
    Explanations

    pakistan and its regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    barang
    0.41
    atein
    0.37
     خبرنگ
    0.37
     reverting
    0.35
     Carlsbad
    0.35
    round
    0.35
    oring
    0.35
    ㄌ
    0.35
    otecas
    0.34
     গুরুদেব
    0.33
    POSITIVE LOGITS
     Taliban
    0.44
     इस्ला
    0.43
     Afghan
    0.41
     Afghans
    0.39
     والی
    0.38
     Access
    0.37
     Tajik
    0.37
     Afgh
    0.37
     porro
    0.36
    Access
    0.36
    Activations Density 0.001%

    No Known Activations