© 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. 31-GEMMASCOPE-2-RES-262K
    7. 190903
    Prev
    Next
    INDEX
    Explanations

    Justin Bieber

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

    existing code, website, crime

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Point
    0.48
    Resources
    0.47
    Elite
    0.47
    LLA
    0.46
     Markets
    0.46
     Infinity
    0.45
    /*
    0.45
    漾
    0.45
    KA
    0.44
    资源
    0.43
    POSITIVE LOGITS
     tenacious
    0.55
    rin
    0.50
    𝐧
    0.49
     vermutlich
    0.48
    rax
    0.48
     clumsy
    0.47
     tyrannical
    0.46
     ترلاسه
    0.46
    ભગ
    0.46
    ią
    0.46
    Activations Density 0.001%

    No Known Activations