© 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. 22-GEMMASCOPE-RES-131K
    7. 25330
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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_22/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
    showing
    -1.39
     SAYS
    -1.26
    脸上的
    -1.26
     SEVENT
    -1.26
    眉头
    -1.25
    reve
    -1.23
    representing
    -1.23
     your
    -1.22
    either
    -1.20
    Lycka
    -1.19
    POSITIVE LOGITS
     after
    1.63
     several
    1.48
     while
    1.34
     when
    1.34
     only
    1.33
     was
    1.27
     three
    1.27
     before
    1.27
     one
    1.24
     two
    1.23
    Activations Density 0.096%

    No Known Activations