© 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. 199160
    Prev
    Next
    INDEX
    Explanations

    stable value, United Kingdom

    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
    ousing
    0.46
    и
    0.44
     predominantly
    0.43
    vad
    0.42
    тор
    0.41
    ำ
    0.41
    so
    0.40
    owered
    0.40
     so
    0.40
    ద్య
    0.40
    POSITIVE LOGITS
     actomyosin
    0.52
    ौनक
    0.49
     ܥ
    0.48
    Ꭴ
    0.48
    jści
    0.48
     enceinte
    0.47
    服务的
    0.47
    erweise
    0.45
     erwarten
    0.45
     asker
    0.45
    Activations Density 0.001%

    No Known Activations