© 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. 239996
    Prev
    Next
    INDEX
    Explanations

    floating markets

    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
    महा
    0.50
    吐槽
    0.49
    馀
    0.45
    partners
    0.44
     भागीदारी
    0.44
    訢
    0.44
    િયો
    0.44
    ور
    0.42
    после
    0.42
    窠
    0.42
    POSITIVE LOGITS
     disclose
    0.50
     inheriting
    0.48
     வந்தது
    0.48
    ക്കുകയും
    0.47
     बरामद
    0.45
     cuánto
    0.45
     hope
    0.44
    anjian
    0.44
     병
    0.44
     vuurp
    0.44
    Activations Density 0.002%

    No Known Activations