© 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. 156365
    Prev
    Next
    INDEX
    Explanations

    "i am" or "i was" statements

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

    my, myself, and I

    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
    被称为
    0.43
    Spatial
    0.42
    蕴
    0.41
    Similarity
    0.41
    Austria
    0.40
    符
    0.39
    蛋白质
    0.38
    ᕈ
    0.38
    Purpose
    0.38
    ॉन
    0.37
    POSITIVE LOGITS
     meiner
    0.79
     meinem
    0.79
     tengo
    0.73
     mijn
    0.72
     myself
    0.71
     veldig
    0.70
     meines
    0.68
     my
    0.67
     मैंने
    0.65
     আমাকে
    0.64
    Activations Density 0.241%

    No Known Activations