© 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-16K
    7. 8344
    Prev
    Next
    INDEX
    Explanations

    URLs with / characters

    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_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
     नाबाल
    0.35
     उक्त
    0.35
    México
    0.33
    ρίου
    0.33
    InnerHTML
    0.33
     altres
    0.32
    绦
    0.32
    傕
    0.32
     Montréal
    0.31
     পরিত্র
    0.31
    POSITIVE LOGITS
     Warum
    0.39
     Як
    0.39
    -
    0.38
     demokrat
    0.36
    }_
    0.35
     comprennent
    0.34
     اعتماد
    0.34
     Nej
    0.34
     peng
    0.34
     যু
    0.33
    Activations Density 0.098%

    No Known Activations