© 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. 15982
    Prev
    Next
    INDEX
    Explanations

    reform and renovation efforts

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

    making changes or improvements

    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
    </strong>
    0.60
    </h3>
    0.59
    </h2>
    0.58
     แม
    0.57
     subcontinent
    0.57
     Database
    0.57
     mancanza
    0.57
     ng
    0.55
     o
    0.55
     is
    0.55
    POSITIVE LOGITS
     modificaciones
    0.91
    改造
    0.91
    修改
    0.83
     modifications
    0.81
    Improvements
    0.74
     alterations
    0.73
     Modifications
    0.73
    л
    0.73
    Changes
    0.73
     alterações
    0.73
    Activations Density 0.122%

    No Known Activations