© 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. 121635
    Prev
    Next
    INDEX
    Explanations

    religious and legal terms

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

    Azure cloud administration

    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
    𝘣
    0.48
    べる
    0.45
     网络
    0.45
    pSensor
    0.45
    𝐛
    0.44
    nienie
    0.44
     multiplicar
    0.44
     加入
    0.43
     模型
    0.43
     mesurer
    0.43
    POSITIVE LOGITS
     থাকলেও
    0.42
    Defaults
    0.41
    -${
    0.40
    IANA
    0.39
    أن
    0.38
     درمان
    0.38
    >…</
    0.38
     बहुमत
    0.38
    ala
    0.38
    icat
    0.37
    Activations Density 0.000%

    No Known Activations