© 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. 189672
    Prev
    Next
    INDEX
    Explanations

    kinds of art and education

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

    polymerase

    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
     höchste
    0.52
    我们在
    0.51
    ö
    0.49
    Ö
    0.49
    我们可以
    0.49
     Gün
    0.48
    标准
    0.47
     Hein
    0.46
    வெ
    0.45
     expressly
    0.44
    POSITIVE LOGITS
     поля
    0.51
    ையிலும்
    0.50
     簡単
    0.49
     دهند
    0.48
     людьми
    0.47
    顆
    0.46
    egd
    0.46
     foto
    0.45
     картин
    0.45
    edge
    0.45
    Activations Density 0.000%

    No Known Activations