© 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-65K
    7. 2726
    Prev
    Next
    INDEX
    Explanations

    first or option

    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_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
    餾
    0.37
    zzo
    0.36
     сложные
    0.35
    几乎
    0.35
    <unused710>
    0.35
    <unused973>
    0.35
    រយៈពេល
    0.34
    almost
    0.34
    ബ്രുവരി
    0.34
    <unused594>
    0.34
    POSITIVE LOGITS
     pertama
    1.03
     первом
    0.87
     Pertama
    0.78
    Ⅰ
    0.77
    １
    0.75
     III
    0.74
    第一
    0.74
     первый
    0.74
     erste
    0.73
     eerste
    0.73
    Activations Density 0.383%

    No Known Activations