© 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-65K
    7. 45021
    Prev
    Next
    INDEX
    Explanations

    conditional comparisons

    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_65k_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
     increment
    0.45
     this
    0.42
     +
    0.41
     >
    0.39
    Þ
    0.39
     desktop
    0.39
     bodysuit
    0.38
     heavyweight
    0.38
     Increment
    0.38
    u
    0.38
    POSITIVE LOGITS
    льники
    0.51
     ошиб
    0.48
    跇
    0.48
    లేని
    0.44
    :");
    0.44
     ошибок
    0.44
    唝
    0.44
    বাধিকার
    0.43
    женности
    0.42
    cevam
    0.42
    Activations Density 0.002%

    No Known Activations