© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 2500
    Prev
    Next
    INDEX
    Explanations

    a followed by a noun

    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
    ↵
    1.17
    in
    1.00
    ل
    0.88
    is
    0.75
    7
    0.71
    5
    0.70
    ام
    0.69
    मध्ये
    0.68
    8
    0.68
    6
    0.65
    POSITIVE LOGITS
     a
    0.86
    ן
    0.64
    人
    0.63
     năng
    0.59
    ﻦ
    0.58
    ﺐ
    0.57
    ことを
    0.56
     quien
    0.55
    нер
    0.55
    0.55
    Activations Density 1.059%

    No Known Activations