© 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. 31-GEMMASCOPE-2-RES-65K
    7. 62261
    Prev
    Next
    INDEX
    Explanations

    Afghanistan, Kabul, Persia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    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
     expt
    0.47
    ബൈ
    0.46
    ając
    0.43
    颀
    0.42
    ेंशन
    0.41
     ہتھیار
    0.41
    蜞
    0.41
    荩
    0.41
     Detroit
    0.40
    Detroit
    0.40
    POSITIVE LOGITS
     Afghan
    1.45
     Afghanistan
    1.42
    Afghanistan
    1.40
    Afghan
    1.36
     Afghans
    1.32
     Kabul
    1.22
     अफगानिस्तान
    1.18
     Afgh
    1.16
     Afgan
    1.12
     افغانستان
    1.00
    Activations Density 0.032%

    No Known Activations