© 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. 51130
    Prev
    Next
    INDEX
    Explanations

    Boxing is, next book

    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
     প্লে
    0.47
     कोलो
    0.45
    鉀
    0.43
     程序
    0.42
    ricanes
    0.41
     および
    0.41
     명령
    0.40
     કર્
    0.40
    プレイ
    0.40
     نوشته
    0.39
    POSITIVE LOGITS
     enterprising
    0.45
     infrastructural
    0.42
     ফাঁস
    0.42
     fraudsters
    0.42
     imageUrl
    0.41
    वान
    0.40
    лена
    0.40
     affordable
    0.39
    ^{*},
    0.39
     unscrupulous
    0.39
    Activations Density 0.064%

    No Known Activations