© 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-262K
    7. 193897
    Prev
    Next
    INDEX
    Explanations

    concise formatting for narratives and data

    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
     जायेगी
    0.46
    vast
    0.43
    ೊಳ
    0.41
     jihad
    0.40
    槭
    0.40
    喿
    0.39
    inib
    0.38
    શે
    0.38
    lst
    0.38
    棫
    0.38
    POSITIVE LOGITS
    คนที่
    0.38
     Wörter
    0.37
    Windows
    0.36
    到一个
    0.36
     μέρος
    0.36
     boring
    0.36
     Pseudomonas
    0.35
     atteints
    0.34
     procl
    0.34
     ×
    0.33
    Activations Density 0.001%

    No Known Activations