© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59725
    Prev
    Next
    INDEX
    Explanations

    calculate probability and arithmetic

    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
     .......
    -2.77
     ratusan
    -2.66
    sandalia
    -2.64
    樒
    -2.61
     ........
    -2.58
    macacão
    -2.58
     เมื่อ
    -2.50
     pembun
    -2.50
     decidedly
    -2.45
     ,"
    -2.45
    POSITIVE LOGITS
    .
    4.06
    In
    2.63
    :”
    2.55
    衕
    2.53
    -”
    2.50
    -“
    2.48
    Just
    2.39
     your
    2.36
    U
    2.36
    !”
    2.34
    Activations Density 0.009%

    No Known Activations