© 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. 51515
    Prev
    Next
    INDEX
    Explanations

    dest/def prefixes

    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
    懶
    0.50
     defined
    0.49
     Kumari
    0.48
     broadened
    0.43
     সূত্রে
    0.42
    ہی
    0.41
    priority
    0.41
    ん
    0.41
    ೋಗ್ಯ
    0.40
     демо
    0.40
    POSITIVE LOGITS
     Dest
    0.59
     dest
    0.56
    dest
    0.50
    Dest
    0.49
     Déf
    0.46
     stabilise
    0.46
     destinada
    0.44
     destin
    0.43
     destiné
    0.43
     guér
    0.43
    Activations Density 0.015%

    No Known Activations