© 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. 16-GEMMASCOPE-2-RES-262K
    7. 16438
    Prev
    Next
    INDEX
    Explanations

    money amounts

    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_16_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
    و
    1.61
    it
    1.26
    在
    1.16
    ad
    1.00
    就
    1.00
    ك
    0.98
    ade
    0.98
    一
    0.96
    ob
    0.94
    بن
    0.93
    POSITIVE LOGITS
     can
    1.14
    ຼ
    1.00
     électronique
    0.97
     arka
    0.96
     are
    0.96
    なる
    0.95
     publiée
    0.93
     abil
    0.91
    ת
    0.91
    ী
    0.90
    Activations Density 0.005%

    No Known Activations