© 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. 35643
    Prev
    Next
    INDEX
    Explanations

    types and patterns

    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
    穵
    0.39
     Barros
    0.36
     SAIL
    0.35
     extract
    0.35
     Fark
    0.35
     ínt
    0.35
    コレート
    0.35
     Replica
    0.35
     銀
    0.34
     Faye
    0.34
    POSITIVE LOGITS
    psilon
    0.63
    系列
    0.48
    型
    0.48
    epsilon
    0.47
     SERIES
    0.45
     फैक्टर
    0.44
    系列的
    0.44
    型的
    0.43
    ullivan
    0.42
    type
    0.42
    Activations Density 0.026%

    No Known Activations