© 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. 55658
    Prev
    Next
    INDEX
    Explanations

    payment methods and transactions

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

    slow, small, dry

    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
    ъл
    0.46
    开
    0.46
    ья
    0.46
    ্লাই
    0.44
     Andre
    0.44
     Royalty
    0.44
    空间
    0.43
    开关
    0.43
    创
    0.43
     Navy
    0.43
    POSITIVE LOGITS
     monitors
    0.56
    kamp
    0.56
    ت
    0.54
     pursuant
    0.51
     ört
    0.49
    kast
    0.48
    ichtet
    0.47
    t
    0.45
    ```
    0.45
     accom
    0.45
    Activations Density 0.000%

    No Known Activations