© 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. 31-GEMMASCOPE-2-RES-262K
    7. 6394
    Prev
    Next
    INDEX
    Explanations

    how and why questions

    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_31_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
     अथवा
    0.30
    ・
    0.27
     অথবা
    0.26
    -
    0.26
    ＆
    0.26
    \
    0.24
    ➢
    0.24
     一
    0.23
    または
    0.23
    ：
    0.23
    POSITIVE LOGITS
     réellement
    0.24
     reali
    0.22
    थिंग
    0.21
     روی
    0.21
     keluar
    0.21
     chemically
    0.21
     worldly
    0.20
    ങ്ങി
    0.20
     supremely
    0.20
     más
    0.19
    Activations Density 0.737%

    No Known Activations