© 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. 4439
    Prev
    Next
    INDEX
    Explanations

    self-referential concepts of process or data

    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
     திரைப்பட
    0.38
     The
    0.37
    <span>
    0.36
     Darren
    0.35
     [[
    0.34
     esetén
    0.34
     Crimson
    0.33
     Stu
    0.33
    0.33
     St
    0.33
    POSITIVE LOGITS
     itself
    0.52
     of
    0.49
    本身
    0.47
    ية
    0.43
     الذي
    0.41
     holder
    0.40
     자체
    0.39
    ة
    0.38
     của
    0.38
     involved
    0.38
    Activations Density 0.470%

    No Known Activations