© 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. 136530
    Prev
    Next
    INDEX
    Explanations

    leadership in bitcoin

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

    quicksort algorithm

    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
    ế
    0.50
    reacted
    0.47
     añad
    0.46
     домаћинства
    0.46
     lao
    0.46
     mì
    0.45
    ]</
    0.44
    ếu
    0.43
     ngành
    0.43
    ]<?
    0.43
    POSITIVE LOGITS
    fusc
    0.53
    Os
    0.49
     Wait
    0.48
     Xmas
    0.48
     Harness
    0.46
     Handle
    0.46
     Chassis
    0.45
     Amnesty
    0.45
     Osborn
    0.45
    ズル
    0.45
    Activations Density 0.005%

    No Known Activations