© 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-65K
    7. 6762
    Prev
    Next
    INDEX
    Explanations

    specific durations or quantities

    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_65k_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
     Tree
    0.57
     Year
    0.53
     Birth
    0.52
     Seasonal
    0.51
    灵
    0.51
     Memory
    0.50
     Common
    0.49
     Living
    0.49
     Collaborative
    0.49
     Syn
    0.48
    POSITIVE LOGITS
     вчера
    0.66
     politici
    0.62
     грошы
    0.62
    esterday
    0.61
    ⵅ
    0.61
    чера
    0.59
     शहर
    0.59
     gestern
    0.59
     நேற்று
    0.58
     turist
    0.58
    Activations Density 0.006%

    No Known Activations