© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74788
    Prev
    Next
    INDEX
    Explanations

    Hong Kong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -1.77
     with
    -1.69
    Because
    -1.65
    Menurutnya
    -1.57
    During
    -1.53
    Like
    -1.50
     {
    -1.45
    When
    -1.44
    Unlike
    -1.42
     géographie
    -1.41
    POSITIVE LOGITS
    ÈNE
    1.45
     is
    1.41
     alcune
    1.36
     valore
    1.34
    still
    1.34
     by
    1.34
    驕
    1.30
     nien
    1.30
    诬
    1.28
     considerare
    1.26
    Activations Density 0.006%

    No Known Activations