© 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. 209878
    Prev
    Next
    INDEX
    Explanations

    caregiverarbitraryGeorgians

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

    construct, explain, or outline

    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
    nueva
    0.52
    Imagen
    0.50
    ंडीज
    0.49
    新手
    0.49
    تم
    0.48
    彝
    0.47
    Images
    0.47
    Screen
    0.46
    ร
    0.46
    нами
    0.46
    POSITIVE LOGITS
     satan
    0.54
     봐
    0.54
     believable
    0.47
     democracia
    0.46
     betrayal
    0.46
     شکل
    0.46
     จึง
    0.46
     demokrasi
    0.46
     depression
    0.45
     ดังนั้น
    0.45
    Activations Density 0.000%

    No Known Activations