© 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. 3351
    Prev
    Next
    INDEX
    Explanations

    class as

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

    technology, process, and systems

    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
    玦
    0.51
    ל
    0.50
    浗
    0.49
    ிற்று
    0.48
    செய்ய
    0.46
     செய்க
    0.45
     रिपीट
    0.45
    ंद
    0.44
    दीय
    0.44
     titre
    0.44
    POSITIVE LOGITS
    ,
    0.50
    ree
    0.46
    name
    0.44
    generators
    0.44
    ↵
    0.43
    ↵↵
    0.43
    ying
    0.43
    ji
    0.43
    lasses
    0.42
     Store
    0.41
    Activations Density 0.000%

    No Known Activations