© 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. 46596
    Prev
    Next
    INDEX
    Explanations

    connecting concepts and states

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

    defining self ("I", "my")

    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
    mark
    0.43
    decimal
    0.43
    OCR
    0.43
    meal
    0.42
    を使って
    0.42
    squared
    0.42
    j
    0.41
    とな
    0.41
    活用
    0.41
    broccoli
    0.41
    POSITIVE LOGITS
     mês
    0.51
     സൃഷ്ട
    0.51
     spéciale
    0.50
     désir
    0.47
    ผู้ชม
    0.46
     নাম্বার
    0.46
     这些
    0.46
     시작하겠습니다
    0.46
     смотря
    0.46
     കമ്മി
    0.45
    Activations Density 0.000%

    No Known Activations