© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50123
    Prev
    Next
    INDEX
    Explanations

    programming and new declarations

    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_65k_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
    เธอ
    0.42
     marad
    0.42
    ilab
    0.41
     landslides
    0.39
     whakar
    0.39
    何を
    0.37
     cơm
    0.37
    //$
    0.35
     ilus
    0.35
    她
    0.35
    POSITIVE LOGITS
     new
    0.51
    new
    0.51
     новой
    0.43
     جديدة
    0.42
     একজন
    0.42
     новий
    0.41
    getBean
    0.40
     नया
    0.39
     নতুন
    0.38
     ASP
    0.38
    Activations Density 0.026%

    No Known Activations