© 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. 22-GEMMASCOPE-RES-131K
    7. 27818
    Prev
    Next
    INDEX
    Explanations

    citations such as [@b5][@b6][@b7]

    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
     this
    -1.73
     while
    -1.66
     which
    -1.66
     that
    -1.60
     or
    -1.55
     during
    -1.45
     after
    -1.45
     when
    -1.39
     if
    -1.38
     should
    -1.38
    POSITIVE LOGITS
     notamment
    1.76
    various
    1.65
     například
    1.59
    several
    1.57
    例如
    1.55
     vários
    1.55
     både
    1.55
    mainly
    1.54
    例えば
    1.53
     plusieurs
    1.50
    Activations Density 0.085%

    No Known Activations