© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 158403
    Prev
    Next
    INDEX
    Explanations

    legal residents are

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

    train the entire model

    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
    MiddleLeft
    0.48
     Tijdens
    0.47
    Escol
    0.45
    Problem
    0.45
    三个
    0.44
    Mga
    0.44
    ı
    0.44
     പഠ
    0.44
    ભગ
    0.44
    随时
    0.43
    POSITIVE LOGITS
     marino
    0.54
     maize
    0.52
     Moab
    0.51
     Мо
    0.50
     মরু
    0.48
     intensiv
    0.47
     mł
    0.46
     interi
    0.45
     Tahoe
    0.45
     Nevada
    0.45
    Activations Density 0.001%

    No Known Activations