© 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. 219230
    Prev
    Next
    INDEX
    Explanations

    green-cleaning services

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

    main codebase or project

    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
    л
    0.50
    
    0.49
    udrait
    0.48
    servlet
    0.47
    北美
    0.46
    marginX
    0.45
    cystic
    0.45
    vercel
    0.45
    ೂರ್ವ
    0.45
    ᱲ
    0.44
    POSITIVE LOGITS
     プロ
    0.51
     schnelle
    0.49
     DDT
    0.49
     Radha
    0.48
     Imran
    0.48
     Wass
    0.47
     sæ
    0.47
     díky
    0.46
     صاحب
    0.46
     Nen
    0.46
    Activations Density 0.001%

    No Known Activations