© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 31443
    Prev
    Next
    INDEX
    Explanations

    Latent Dirichlet Allocation (LDA) topics

    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_all/layer_41_width_262k_l0_big
    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
     lan
    0.41
    ленной
    0.39
    pset
    0.38
    সংখ্য
    0.38
    刄
    0.38
    जेक्शन
    0.38
     attravers
    0.38
    кия
    0.38
     kilomet
    0.38
    ᵕ
    0.38
    POSITIVE LOGITS
     topics
    1.13
     topic
    1.09
     Topics
    1.04
     Topic
    1.04
    topic
    1.02
    topics
    1.01
    Topics
    0.99
    Topic
    0.98
     topik
    0.80
    话题
    0.79
    Activations Density 0.001%

    No Known Activations