© 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. 31-GEMMASCOPE-2-RES-262K
    7. 125816
    Prev
    Next
    INDEX
    Explanations

    actions and requirements

    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_31_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
     любо
    0.47
     Sturgeon
    0.46
    доль
    0.45
     пу
    0.45
     Tokugawa
    0.44
     miš
    0.44
    깆
    0.44
     Algon
    0.44
     പ്രത്യേ
    0.43
    悯
    0.43
    POSITIVE LOGITS
     refined
    0.52
     requested
    0.52
    io
    0.51
    ag
    0.49
    વામાં
    0.48
    c
    0.48
    Q
    0.47
     subscriber
    0.46
    q
    0.46
    present
    0.46
    Activations Density 0.017%

    No Known Activations