© 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. 47778
    Prev
    Next
    INDEX
    Explanations

    comparison, difference, quantity, debate

    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
    INO
    0.47
     Indians
    0.44
    0.44
                    
    0.42
    0.40
     credibility
    0.39
    一段
    0.38
    朴
    0.38
    धा
    0.38
    原始
    0.38
    POSITIVE LOGITS
     दाब
    0.47
     approu
    0.47
     inégal
    0.46
     அதன்
    0.44
    ഫ്
    0.44
    ائش
    0.44
     fièvre
    0.44
     fian
    0.43
     sanguí
    0.43
     défi
    0.43
    Activations Density 0.001%

    No Known Activations