© 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. 183647
    Prev
    Next
    INDEX
    Explanations

    boxing, basketball, wrestling, sports figures

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

    Orc

    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
    सरी
    0.47
     우리의
    0.46
     صفحۀ
    0.45
     🥰
    0.44
     वगैर
    0.43
    луйста
    0.42
     indign
    0.42
     поговорим
    0.42
     Tjiwarl
    0.42
     rethinking
    0.42
    POSITIVE LOGITS
    SVM
    0.58
    Place
    0.50
    Ray
    0.48
    WWE
    0.48
    Approx
    0.47
    Apache
    0.46
    逆
    0.45
    Roll
    0.44
    Sport
    0.43
    Bus
    0.43
    Activations Density 0.001%

    No Known Activations