© 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. 233816
    Prev
    Next
    INDEX
    Explanations

    woke up, blog post

    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
    COT
    0.46
    )}.
    0.45
     ingot
    0.45
     சுண்ணாம்பு
    0.44
    CHO
    0.44
    }`,
    0.43
    arote
    0.43
     "@/
    0.43
     LINKS
    0.42
    포츠
    0.42
    POSITIVE LOGITS
    義務
    0.54
     Veranst
    0.48
     Xerox
    0.48
     จำนวน
    0.47
    وأ
    0.45
     विधानसभा
    0.44
    Џ
    0.44
     keine
    0.44
     Snapchat
    0.43
    رويج
    0.43
    Activations Density 0.001%

    No Known Activations