© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46596
    Prev
    Next
    INDEX
    Explanations

    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-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
    OCR
    0.41
    roud
    0.40
    j
    0.40
    ERC
    0.39
    筋
    0.39
    box
    0.39
    shield
    0.39
    decimal
    0.39
    meal
    0.38
    тить
    0.38
    POSITIVE LOGITS
     mês
    0.57
     spéciale
    0.52
    “-
    0.48
     സൃഷ്ട
    0.46
     miesią
    0.45
    
    0.45
     două
    0.44
     കമ്മി
    0.44
     désir
    0.43
    ഫ
    0.43
    Activations Density 0.001%

    No Known Activations