© 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. 2332
    Prev
    Next
    INDEX
    Explanations

    NEXT BACK

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

    meow

    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
     sním
    0.35
     whakar
    0.34
     ahuv
    0.34
    ➌
    0.33
     manuss
    0.33
     kroz
    0.33
     rapaz
    0.33
     duckys
    0.33
     fallait
    0.32
     parois
    0.32
    POSITIVE LOGITS
    0.43
    _
    0.38
    ா
    0.37
    </h4>
    0.35
    С
    0.34
          
    0.34
    text
    0.34
    ----------------
    0.34
    etc
    0.34
    </strong>
    0.33
    Activations Density 0.009%

    No Known Activations