© 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. 212744
    Prev
    Next
    INDEX
    Explanations

    back or legacy applications

    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
     väik
    0.42
     পাস
    0.41
    యర్
    0.40
     کوچک
    0.38
     малень
    0.38
     pequeña
    0.37
     pequeño
    0.37
    Я
    0.37
     असिस्ट
    0.37
     छोटे
    0.37
    POSITIVE LOGITS
     Carmichael
    0.41
    endenza
    0.38
    methylation
    0.38
    mutex
    0.37
     electrochemical
    0.37
     deportation
    0.37
    march
    0.37
    itectura
    0.37
    tray
    0.37
    ifical
    0.36
    Activations Density 0.000%

    No Known Activations