© 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. 112389
    Prev
    Next
    INDEX
    Explanations

    entry level documents evidence Queen grav papers

    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
     trendy
    0.49
     ignorant
    0.49
     plaster
    0.48
     வீட்டு
    0.47
    颼
    0.46
     nerve
    0.46
     blind
    0.46
     ignition
    0.45
     wildest
    0.45
     seventh
    0.43
    POSITIVE LOGITS
     \%)$
    0.46
    区
    0.44
    CCCCCCCC
    0.42
    купки
    0.42
    äfte
    0.41
    ে
    0.41
    
    0.41
    ENTRY
    0.40
     округу
    0.40
     می‌توان
    0.39
    Activations Density 0.003%

    No Known Activations