© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128777
    Prev
    Next
    INDEX
    Explanations

    who vs whom

    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_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
    。
    0.35
    ,
    0.34
    ー
    0.34
    ;
    0.33
    ，
    0.31
    ↵↵
    0.30
     (
    0.30
    н
    0.30
    /
    0.29
    <0xEF>
    0.29
    POSITIVE LOGITS
    服务的
    0.27
     Reakt
    0.27
     myocard
    0.26
    人都
    0.26
     Ressourcen
    0.25
     Malware
    0.25
     Mutant
    0.25
     entrop
    0.25
     amerikan
    0.24
     croche
    0.24
    Activations Density 0.109%

    No Known Activations