© 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-65K
    7. 65370
    Prev
    Next
    INDEX
    Explanations

    encourages bladder expansion

    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_65k_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
     Specifications
    0.51
     Using
    0.48
     Summit
    0.46
     Types
    0.44
     Guys
    0.44
    喩
    0.43
     using
    0.41
     Spending
    0.41
     Sponsored
    0.41
    ল
    0.41
    POSITIVE LOGITS
    ZE
    0.50
    kań
    0.48
    λημα
    0.48
    éreo
    0.47
     estím
    0.47
    tores
    0.46
    aneus
    0.46
    änglich
    0.46
    ্রেক
    0.45
    iel
    0.45
    Activations Density 0.033%

    No Known Activations