© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 31462
    Prev
    Next
    INDEX
    Explanations

    informational purposes only

    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
     abar
    0.38
    lus
    0.37
     séparation
    0.36
    撣
    0.36
     ervoor
    0.35
     indicative
    0.34
     elevado
    0.33
    avio
    0.33
     rounds
    0.33
     состави
    0.33
    POSITIVE LOGITS
    ListComponent
    0.40
    ೆಂದು
    0.39
    डू
    0.35
    統領
    0.35
    ';"+
    0.35
    ごとに
    0.35
    集團
    0.35
    🛌
    0.35
    pesar
    0.34
    ovem
    0.34
    Activations Density 0.001%

    No Known Activations