© 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. 33315
    Prev
    Next
    INDEX
    Explanations

    questions answered

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

    time and development

    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
     undeniably
    0.46
    ную
    0.45
    圧
    0.43
     complained
    0.43
    伏
    0.42
    CommandBuffer
    0.42
     resented
    0.42
     patch
    0.41
    VAR
    0.41
     irrepar
    0.41
    POSITIVE LOGITS
    जिए
    0.49
     Ethical
    0.46
     ท่าน
    0.46
     หล
    0.45
    จะ
    0.44
    hidupan
    0.44
     ลอง
    0.44
    委員會
    0.44
     ऐ
    0.43
    ท่าน
    0.42
    Activations Density 0.000%

    No Known Activations