© 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. 201273
    Prev
    Next
    INDEX
    Explanations

    Oliver Cromwell

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

    predicting sequences after common words

    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
    finance
    0.52
     農
    0.52
     cany
    0.51
     マン
    0.50
     ಕಂಡು
    0.49
     簡単
    0.48
     अदानी
    0.46
    शासित
    0.46
     Citibank
    0.46
     sumptuous
    0.46
    POSITIVE LOGITS
    блема
    0.48
    тья
    0.46
    сту
    0.43
    公开
    0.43
    ృ
    0.42
     D
    0.41
    v
    0.40
    чку
    0.39
    в
    0.39
     Д
    0.38
    Activations Density 0.000%

    No Known Activations