© 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. 31-GEMMASCOPE-2-RES-16K
    7. 531
    Prev
    Next
    INDEX
    Explanations

    section headers and technical explanations

    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
    あるいは
    0.29
     ಅಥವಾ
    0.24
     तसेच
    0.23
    eserc
    0.22
     president
    0.22
    <unused429>
    0.22
    場合には
    0.22
     কিংবা
    0.21
    之类的
    0.21
    ซึ่ง
    0.21
    POSITIVE LOGITS
     vs
    0.35
     Basics
    0.33
    </h2>
    0.33
    </h3>
    0.31
    </h4>
    0.31
     &
    0.29
     통한
    0.29
     Revisited
    0.29
     -
    0.28
     Role
    0.28
    Activations Density 5.458%

    No Known Activations