© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 133353
    Prev
    Next
    INDEX
    Explanations

    defining acronyms or terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     keb
    0.46
     banner
    0.40
     lagoons
    0.40
     frog
    0.39
     admissible
    0.39
     tab
    0.39
     consente
    0.38
    ョ
    0.38
     allows
    0.37
     permet
    0.37
    POSITIVE LOGITS
     altera
    0.43
     disson
    0.42
     оса
    0.40
     FedEx
    0.39
    psum
    0.38
     владель
    0.38
     ἢ
    0.38
    Electro
    0.38
    オーナー
    0.38
     klant
    0.37
    Activations Density 0.003%

    No Known Activations