© 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. 20578
    Prev
    Next
    INDEX
    Explanations

    breakdowns of why and how

    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
    毽
    0.40
    鈕
    0.40
     চেষ্টা
    0.38
     sử
    0.38
     사용하여
    0.38
     cierta
    0.38
    িয়ান
    0.37
     utilizzare
    0.37
     lubricating
    0.36
     dissu
    0.36
    POSITIVE LOGITS
    战争
    0.47
    और
    0.46
    ద
    0.44
    Firstly
    0.43
    you
    0.42
    moja
    0.41
    льне
    0.41
    લો
    0.41
     Firstly
    0.40
     doenças
    0.40
    Activations Density 0.099%

    No Known Activations