© 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-16K
    7. 12368
    Prev
    Next
    INDEX
    Explanations

    HTTP requests

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

    network protocol headers

    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_16k_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
    籵
    0.44
    desa
    0.44
     Educa
    0.42
    对称
    0.42
     اہ
    0.40
    IsResolver
    0.40
    udes
    0.40
    蒻
    0.40
    desk
    0.40
     корректи
    0.39
    POSITIVE LOGITS
     line
    0.47
     HTTP
    0.44
     NIST
    0.44
     motorcycle
    0.42
     beef
    0.42
     motorcycles
    0.42
     header
    0.42
     Neg
    0.42
     anore
    0.42
    getHeader
    0.41
    Activations Density 0.052%

    No Known Activations