© 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. 41-GEMMASCOPE-2-RES-262K
    7. 30418
    Prev
    Next
    INDEX
    Explanations

    Tehran

    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_all/layer_41_width_262k_l0_big
    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
     cup
    0.88
    Cup
    0.86
     Cup
    0.82
    杯
    0.76
    컵
    0.74
    cup
    0.73
     Cups
    0.73
    Cups
    0.71
     cups
    0.69
    カップ
    0.69
    POSITIVE LOGITS
     Test
    0.48
    TestSuite
    0.47
     TES
    0.44
     Tehran
    0.42
     tes
    0.42
    ジャン
    0.41
     테
    0.39
     Tests
    0.38
     тэ
    0.38
     Полу
    0.38
    Activations Density 0.001%

    No Known Activations