© 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-16K
    7. 6890
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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_16k_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
    زال
    0.49
    կ
    0.48
    楖
    0.47
     왔
    0.47
    ناب
    0.46
    <0xBD>
    0.46
    ാല
    0.45
    راح
    0.45
    <0xBB>
    0.44
    Ӹ
    0.44
    POSITIVE LOGITS
     психологи
    0.50
    IVATE
    0.42
     يعمل
    0.42
     imports
    0.41
     смотреть
    0.41
    imports
    0.41
     cualidades
    0.41
     હંમે
    0.41
     overworked
    0.41
    વાથી
    0.40
    Activations Density 0.015%

    No Known Activations