© 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. 19344
    Prev
    Next
    INDEX
    Explanations

    During

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

    especially during

    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
     typically
    0.45
    ↵
    0.44
     suelen
    0.44
    funding
    0.43
     veya
    0.43
     suele
    0.43
    ارع
    0.41
     publication
    0.41
     generalmente
    0.41
    もしくは
    0.41
    POSITIVE LOGITS
    During
    0.54
     DURING
    0.54
     במהלך
    0.53
    鹛
    0.48
     특히
    0.47
    특히
    0.47
     tijdens
    0.45
     실험
    0.45
     During
    0.45
    实验
    0.45
    Activations Density 0.000%

    No Known Activations