© 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. 40-GEMMASCOPE-2-RES-65K
    7. 52025
    Prev
    Next
    INDEX
    Explanations

    key to secrets and mysteries

    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_40_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
    Assess
    0.41
    illings
    0.39
     assessed
    0.38
     citations
    0.36
     শরণার্থী
    0.36
    綽
    0.35
    مرات
    0.35
     checkpoint
    0.35
     Apps
    0.34
     geprü
    0.34
    POSITIVE LOGITS
     mystery
    1.27
     mysteries
    1.27
     unravel
    1.20
    謎
    1.16
     রহস্য
    1.16
     unlocking
    1.15
     uncovering
    1.14
     unveil
    1.13
    mystery
    1.13
    揭
    1.12
    Activations Density 0.099%

    No Known Activations