© 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. 236122
    Prev
    Next
    INDEX
    Explanations

    Non-English words and emojis

    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
     zonder
    0.48
     (`
    0.48
     fără
    0.48
    的行为
    0.44
     anorexia
    0.43
     работо
    0.43
     lovingly
    0.42
     mView
    0.42
     volgens
    0.42
     функції
    0.42
    POSITIVE LOGITS
    🎏
    0.45
    ítés
    0.43
    čných
    0.43
    丷
    0.43
     شکار
    0.42
     sampah
    0.42
     diterapkan
    0.41
    ǝ
    0.41
    Brexit
    0.41
    🗯
    0.41
    Activations Density 0.002%

    No Known Activations