© 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-262K
    7. 135148
    Prev
    Next
    INDEX
    Explanations

    potentially impactful version

    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_262k_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
     চোখের
    0.45
    br
    0.45
    bra
    0.43
     आंखों
    0.43
    gr
    0.40
    every
    0.40
    िए
    0.39
    t
    0.39
    sw
    0.38
    case
    0.38
    POSITIVE LOGITS
     okaza
    0.40
    وجد
    0.39
    क्यात
    0.37
     divid
    0.36
    বাধিকার
    0.36
    ڦ
    0.36
     estamp
    0.36
     Fulham
    0.36
    ittelt
    0.36
     remembered
    0.36
    Activations Density 0.005%

    No Known Activations