© 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. 126021
    Prev
    Next
    INDEX
    Explanations

    liability, God, highest standards, thou, only allowed

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

    breakdown

    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
    ëren
    0.51
    넌
    0.51
    oscopy
    0.50
    artige
    0.50
    Colors
    0.49
     ছিলেন
    0.48
    运行时
    0.48
    ogenicity
    0.48
    Ethan
    0.45
    Thoughts
    0.45
    POSITIVE LOGITS
     salle
    0.49
    ﺲ
    0.49
     naud
    0.48
     promenade
    0.46
    uala
    0.46
     stroll
    0.46
     buy
    0.45
    ชม
    0.45
     frans
    0.45
     unified
    0.45
    Activations Density 0.000%

    No Known Activations