© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91453
    Prev
    Next
    INDEX
    Explanations

    charters, chart, constitution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ní
    0.52
    '
    0.50
    器
    0.49
     divine
    0.49
     Ví
    0.49
     bless
    0.47
     stro
    0.47
    s
    0.46
     fruto
    0.46
     Kell
    0.45
    POSITIVE LOGITS
    ambut
    0.51
    asidd
    0.50
    habitation
    0.48
    Membership
    0.47
    anjutnya
    0.47
     зарабаты
    0.47
    enteri
    0.46
    class
    0.46
     تعلیم
    0.46
    設け
    0.45
    Activations Density 0.002%

    No Known Activations