© 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. 10439
    Prev
    Next
    INDEX
    Explanations

    foreign language text

    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
     our
    0.28
     ALL
    0.28
     BOTH
    0.28
    m
    0.27
     ESPE
    0.26
     unser
    0.26
     damal
    0.26
     tämä
    0.26
     IMEI
    0.25
    改めて
    0.25
    POSITIVE LOGITS
     inzwischen
    0.34
     लेकिन
    0.34
     rifi
    0.34
    结婚
    0.32
     لیکن
    0.32
     फिलहाल
    0.30
    㬹
    0.30
     mittlerweile
    0.30
    現在は
    0.29
     riman
    0.29
    Activations Density 0.000%

    No Known Activations