© 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. 81430
    Prev
    Next
    INDEX
    Explanations

    production, leader, or Exception

    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
    /
    0.56
    L
    0.56
    0.52
     To
    0.52
    Ε
    0.51
     Prado
    0.50
     and
    0.50
    د
    0.50
    から
    0.50
     Layer
    0.50
    POSITIVE LOGITS
     الدراسة
    0.48
    स्ट्रेल
    0.47
     roasted
    0.46
     .^{
    0.45
    kjhtml
    0.45
     thisTrial
    0.44
    రోగ
    0.44
    źni
    0.44
    getStudentNo
    0.43
    த்துள்ளார்
    0.42
    Activations Density 0.001%

    No Known Activations