© 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. 16-GEMMASCOPE-2-RES-262K
    7. 139116
    Prev
    Next
    INDEX
    Explanations

    contempt

    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_16_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
     I
    0.72
     P
    0.58
    ’
    0.57
    ings
    0.56
    ution
    0.54
    INES
    0.54
    I
    0.53
    н
    0.53
      
    0.52
    ures
    0.52
    POSITIVE LOGITS
     marav
    0.61
    ﻊ
    0.58
    جموعة
    0.57
    𝗩
    0.57
    től
    0.56
    জ
    0.56
    ūsų
    0.55
    소를
    0.55
    زيد
    0.55
    zieć
    0.55
    Activations Density 0.001%

    No Known Activations