© 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. 53545
    Prev
    Next
    INDEX
    Explanations

    ratio scale

    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
    in
    0.49
     horribly
    0.46
    &
    0.45
     in
    0.43
     quantify
    0.42
     verify
    0.41
     v
    0.40
    χα
    0.40
     fought
    0.39
     minimize
    0.39
    POSITIVE LOGITS
     Cómo
    0.46
    യാണ്
    0.45
    Tienes
    0.45
    に向
    0.45
    Enlaces
    0.43
    Puedes
    0.43
     مختلفة
    0.43
    Primero
    0.43
    diendo
    0.42
    
    0.42
    Activations Density 0.002%

    No Known Activations