© 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-262K
    7. 168687
    Prev
    Next
    INDEX
    Explanations

    model modelversions and their parameters

    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
    사이
    0.47
    mail
    0.39
    _,
    0.38
    는
    0.38
     &
    0.38
     postal
    0.37
     어
    0.36
    문
    0.36
    르는
    0.36
    카페
    0.36
    POSITIVE LOGITS
    쁘
    0.43
    嗬
    0.43
    াকাছি
    0.42
     Shenzhen
    0.39
    Xiaomi
    0.39
     thru
    0.38
    व्
    0.38
    ⟣
    0.38
     गटा
    0.38
    Specifically
    0.38
    Activations Density 0.005%

    No Known Activations