© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9345
    Prev
    Next
    INDEX
    Explanations

    club, service, place names

    np_acts-logits-general · gemini-2.5-flash-lite

    code comments and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ፣
    0.55
     ፣
    0.50
    ၊
    0.49
    等等
    0.48
    、
    0.48
    ﹑
    0.48
     등이
    0.47
     、
    0.47
     тощо
    0.46
    ،
    0.46
    POSITIVE LOGITS
     चमकदार
    0.41
    ÑO
    0.38
    endido
    0.36
     Way
    0.35
     நேரம்
    0.35
     §
    0.34
     সম্ভাবনা
    0.34
    inkin
    0.34
    数为
    0.34
     Magical
    0.33
    Activations Density 0.130%

    No Known Activations