© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12831
    Prev
    Next
    INDEX
    Explanations

    date and time patterns

    np_acts-logits-general · gemini-2.5-flash-lite

    HTTP headers and cookies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    粒子
    0.44
    呫
    0.44
     замі
    0.44
    IsResolver
    0.42
     Omphalodes
    0.41
    Assalamualaikum
    0.41
     યો
    0.40
    董事
    0.40
    詰
    0.40
    对称
    0.39
    POSITIVE LOGITS
     Neg
    0.46
     line
    0.46
     storefront
    0.44
    line
    0.41
     training
    0.40
     catalog
    0.40
    로
    0.40
    ेंज
    0.39
     HEAD
    0.39
     modeling
    0.38
    Activations Density 0.004%

    No Known Activations