© 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. 239174
    Prev
    Next
    INDEX
    Explanations

    Starbucks starts serving pumpkin spice

    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
     లేదా
    0.58
     وضع
    0.54
     hadron
    0.54
     ឬ
    0.53
     یا
    0.52
     அல்லது
    0.52
     করার
    0.51
     優
    0.51
     Це
    0.50
     termen
    0.50
    POSITIVE LOGITS
    j
    0.62
    science
    0.52
    g
    0.51
    t
    0.49
    sc
    0.49
    лі
    0.48
    growing
    0.47
    า
    0.47
    culture
    0.47
    n
    0.47
    Activations Density 0.001%

    No Known Activations