© 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. 45314
    Prev
    Next
    INDEX
    Explanations

    additional, supplementary, extension

    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
    SdkVersion
    0.44
    ᖃ
    0.40
     बेरोजगारी
    0.40
    ěl
    0.39
    礙
    0.39
    ው
    0.39
    عى
    0.38
    ‌,
    0.38
     জাতিসঙ্ঘ
    0.38
     cât
    0.38
    POSITIVE LOGITS
     supplementary
    1.48
     supplemental
    1.48
     supplement
    1.30
     supplementing
    1.30
     additional
    1.27
     дополни
    1.23
     tambahan
    1.22
     Supplementary
    1.21
    补充
    1.18
     дополнительных
    1.18
    Activations Density 0.276%

    No Known Activations