© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226929
    Prev
    Next
    INDEX
    Explanations

    strong, everywhere, sure, many, saves, enhancement, much, speaking, Sunday

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     বয়
    0.45
     bitches
    0.44
    {(
    0.44
    StaticHandler
    0.42
    잘
    0.42
     shutdowns
    0.42
     Tutorials
    0.42
     uncles
    0.41
    টি
    0.40
    diy
    0.40
    POSITIVE LOGITS
    绵
    0.47
    いです
    0.46
    াল
    0.46
    <0x94>
    0.45
    航空
    0.45
     அலெ
    0.45
    mck
    0.45
    жкой
    0.44
     ricos
    0.44
    σε
    0.43
    Activations Density 0.000%

    No Known Activations