© 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-RES-262K
    7. 221331
    Prev
    Next
    INDEX
    Explanations

    Arabic particles and English 'an'

    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_40_width_262k_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
     पिया
    0.44
    POR
    0.41
    ሐ
    0.38
     pharmacist
    0.38
     दिख
    0.38
     Buna
    0.38
    ভাল
    0.37
     символ
    0.37
     করবার
    0.37
    徠
    0.37
    POSITIVE LOGITS
    감을
    0.47
    зацию
    0.45
    هم
    0.43
    strument
    0.42
    اقه
    0.42
     شاء
    0.38
    zyme
    0.38
    ogne
    0.38
    esthesia
    0.37
    ique
    0.37
    Activations Density 0.001%

    No Known Activations