© 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. 73042
    Prev
    Next
    INDEX
    Explanations

    isn't contraction

    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
    弍
    -2.78
    a
    -2.70
    ሷ
    -2.66
    ୪
    -2.63
     become
    -2.63
    ّر
    -2.53
     emphas
    -2.48
    焄
    -2.48
    ᯾
    -2.42
    ︲
    -2.39
    POSITIVE LOGITS
     isn
    3.27
    {
    3.20
     Then
    3.00
     This
    2.89
     书法
    2.67
     alors
    2.55
     tuss
    2.41
     There
    2.41
     depriving
    2.41
    ?"
    2.39
    Activations Density 0.014%

    No Known Activations