© 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. 54863
    Prev
    Next
    INDEX
    Explanations

    Latex, healthcare, Clark Kent

    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
    Ꮿ
    0.48
     zusätz
    0.48
     verticals
    0.47
     größ
    0.46
     واپ
    0.45
     zám
    0.45
     இட
    0.44
     jamás
    0.44
     Elekt
    0.43
     vrijed
    0.43
    POSITIVE LOGITS
    0.54
    ỡng
    0.49
     fm
    0.47
     会
    0.45
     Download
    0.44
     می
    0.43
     बदले
    0.43
     제
    0.43
    কি
    0.42
     Emulator
    0.42
    Activations Density 0.002%

    No Known Activations