© 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. 26713
    Prev
    Next
    INDEX
    Explanations

    dependency 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
    Helen
    0.40
     அமிலம்
    0.40
     выру
    0.40
     स्क्रीन
    0.40
    onson
    0.38
    รางวัล
    0.38
     น
    0.38
     Johanna
    0.38
     விச
    0.38
    pecu
    0.38
    POSITIVE LOGITS
     immerse
    0.40
     প্রতিশ্রুতি
    0.40
    寨
    0.39
     Upgrade
    0.38
    imported
    0.38
    去看
    0.38
     upgrade
    0.37
     Himal
    0.37
    getcwd
    0.37
     Provision
    0.37
    Activations Density 0.000%

    No Known Activations