© 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. 6459
    Prev
    Next
    INDEX
    Explanations

    prohibiting sexual or violent content

    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
     Configuring
    0.47
     食品
    0.46
     電気
    0.46
     memperoleh
    0.45
     affordability
    0.43
     部
    0.42
     ማን
    0.42
    այն
    0.41
    ี้ยว
    0.41
    getahuan
    0.41
    POSITIVE LOGITS
     tám
    0.52
     in
    0.51
     pone
    0.49
    s
    0.48
     Halifax
    0.48
     семи
    0.47
     él
    0.45
     září
    0.45
    rainbow
    0.45
    कविता
    0.45
    Activations Density 0.001%

    No Known Activations