© 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. 231801
    Prev
    Next
    INDEX
    Explanations

    abandon or support services

    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
    نر
    0.50
     рит
    0.49
     اصلي
    0.47
     прикла
    0.47
     vutto
    0.47
    Ķ
    0.46
    +"/"+
    0.45
     дети
    0.45
    Գ
    0.45
     потім
    0.44
    POSITIVE LOGITS
     permission
    0.54
    has
    0.52
     stomach
    0.48
     have
    0.47
    去世
    0.46
    permission
    0.46
     परवानगी
    0.45
    死的
    0.45
    områ
    0.45
     mayonnaise
    0.45
    Activations Density 0.000%

    No Known Activations