© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10013
    Prev
    Next
    INDEX
    Explanations

    must be explored

    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_16k_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
     naudoj
    0.34
    itoare
    0.34
    ात
    0.34
     ਵ
    0.33
    斯
    0.32
    being
    0.32
     被
    0.32
    িখিত
    0.32
     να
    0.31
    tie
    0.31
    POSITIVE LOGITS
     Brown
    0.33
     Heartland
    0.33
    లోకి
    0.33
     models
    0.32
    షన్‌
    0.32
     jersey
    0.32
     kitten
    0.32
     sunglasses
    0.31
     ActionMode
    0.31
    恳
    0.31
    Activations Density 0.039%

    No Known Activations