© 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. 236536
    Prev
    Next
    INDEX
    Explanations

    sports, production, technology, and difficulty

    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
     motives
    0.49
     διάρκ
    0.48
    स्तों
    0.47
    はある
    0.47
    iyordu
    0.46
     intentions
    0.46
    Ⴊ
    0.45
     สถาน
    0.45
     ティ
    0.44
     voucher
    0.44
    POSITIVE LOGITS
    Texto
    0.44
    subset
    0.43
     Kullan
    0.43
     synchronized
    0.41
     translate
    0.40
    算法
    0.39
    檔
    0.39
     Clase
    0.39
     Texto
    0.39
     Wanneer
    0.38
    Activations Density 0.001%

    No Known Activations