© 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. 15134
    Prev
    Next
    INDEX
    Explanations

    people captured

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

    specific concepts and categories

    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
     పలు
    0.45
    ឱ្យ
    0.43
    ؤ
    0.41
    Concluding
    0.41
     similarities
    0.40
    成為
    0.39
    ٻ
    0.38
    정을
    0.38
     titt
    0.38
     cytoskeleton
    0.37
    POSITIVE LOGITS
    的一部分
    0.75
     geworden
    0.64
     거고
    0.61
     gewesen
    0.58
    なのですが
    0.58
    but
    0.57
    தாகும்
    0.56
     geweest
    0.55
    んですが
    0.54
    ではありません
    0.54
    Activations Density 0.248%

    No Known Activations