© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 9475
    Prev
    Next
    INDEX
    Explanations

    you for

    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_16k_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
     ਅ
    0.55
     និង
    0.54
     Що
    0.52
     comienzo
    0.52
     admirable
    0.50
     ແລະ
    0.49
     recrystall
    0.49
     улучшения
    0.48
     observations
    0.47
     ڏ
    0.47
    POSITIVE LOGITS
     for
    0.61
    ላሉ
    0.57
     to
    0.52
    Lloyd
    0.48
     from
    0.47
    pathy
    0.46
    特定の
    0.44
    勒
    0.44
     by
    0.44
     Né
    0.44
    Activations Density 0.035%

    No Known Activations