© 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. 12731
    Prev
    Next
    INDEX
    Explanations

    specifications, rate, author, date, ends

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

    key features

    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
    StackTrace
    0.37
    全新的
    0.37
    ynchronous
    0.36
     axisymmetric
    0.36
    rawberry
    0.36
     ()=>{
    0.35
     -!
    0.34
     xhrObj
    0.34
    yscrapers
    0.33
     surjective
    0.32
    POSITIVE LOGITS
    是否有
    0.39
     מספר
    0.38
     प्रकार
    0.38
    是否
    0.38
     אם
    0.37
    ?»
    0.37
    ²/
    0.37
     aantal
    0.37
     ถ้า
    0.37
    人数
    0.37
    Activations Density 0.050%

    No Known Activations