© 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. 5331
    Prev
    Next
    INDEX
    Explanations

    RSS Feed submission

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

    desperately wanting something

    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
    在了
    0.54
    4
    0.50
    had
    0.47
    successfully
    0.47
     successfully
    0.46
     consistently
    0.45
    6
    0.45
    took
    0.44
     tenían
    0.44
     করেছিলেন
    0.44
    POSITIVE LOGITS
    渴望
    0.52
     rumoured
    0.49
     nuove
    0.49
    危险
    0.49
    噂
    0.49
     kvůli
    0.49
    覬
    0.49
     desperate
    0.48
    预约
    0.48
     wegen
    0.48
    Activations Density 0.000%

    No Known Activations