© 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. 49155
    Prev
    Next
    INDEX
    Explanations

    places and clothing

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

    code blocks or formatting

    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
     seize
    0.44
    ↵
    0.43
     recoup
    0.42
     volut
    0.42
    その
    0.41
     जिससे
    0.41
    ע
    0.41
     carre
    0.40
    s
    0.40
    ש
    0.40
    POSITIVE LOGITS
    架构
    0.52
    槸
    0.47
    ệp
    0.43
    飞机
    0.42
     Máy
    0.42
     phylogeny
    0.42
    轴
    0.42
     xuân
    0.42
     Örneğin
    0.41
     તરીકે
    0.41
    Activations Density 0.001%

    No Known Activations