© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1613
    Prev
    Next
    INDEX
    Explanations

    organizing and explaining information

    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
     Its
    0.37
     its
    0.28
    Its
    0.28
     cannot
    0.27
     其
    0.27
     Upon
    0.26
       
    0.26
    その
    0.25
     dessen
    0.25
    其
    0.25
    POSITIVE LOGITS
     things
    0.54
     cosas
    0.44
     everything
    0.41
     ব্যাপারটা
    0.40
     چیز
    0.40
     şeyler
    0.40
     şeyi
    0.39
    Things
    0.38
    everything
    0.38
     चीज़
    0.37
    Activations Density 0.896%

    No Known Activations