© 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. 40-GEMMASCOPE-2-RES-262K
    7. 10123
    Prev
    Next
    INDEX
    Explanations

    vector embeddings for clustering

    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_40_width_262k_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
    䏲
    0.44
    هور
    0.43
     పెట్ట
    0.43
     डिजाईन
    0.43
    讥
    0.42
    चुरी
    0.42
    webBrowser
    0.42
    畚
    0.42
    chedule
    0.42
    ⨔
    0.42
    POSITIVE LOGITS
     clustering
    1.27
     dimensionality
    1.17
     Clustering
    1.17
     PCA
    1.16
     embeddings
    1.12
     unsupervised
    1.06
    PCA
    1.02
     subspace
    1.02
    clustering
    1.01
     cluster
    1.00
    Activations Density 0.139%

    No Known Activations