© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 711
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     convened
    0.72
     przedsiębior
    0.72
     giỏi
    0.70
     صلاحیت
    0.70
    🏬
    0.70
    CompliancePolicy
    0.69
    🏛
    0.69
    🕍
    0.69
     使っ
    0.68
     ciências
    0.67
    POSITIVE LOGITS
     texture
    1.80
     discoloration
    1.66
     edges
    1.57
     ridges
    1.53
     whitish
    1.53
     imperfections
    1.52
     mottled
    1.52
     textures
    1.51
     streaks
    1.48
     roughness
    1.46
    Activations Density 1.856%

    No Known Activations