© 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. 39040
    Prev
    Next
    INDEX
    Explanations

    identifiers and numbers

    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
     of
    -1.34
     year
    -1.23
     would
    -1.18
     or
    -1.18
     for
    -1.15
     only
    -1.14
     areas
    -1.05
     及
    -1.05
     years
    -1.05
     might
    -1.04
    POSITIVE LOGITS
     satisfactor
    1.33
     rues
    1.33
     Erfüllung
    1.25
     dîner
    1.24
     MATTERS
    1.23
     thorium
    1.23
    ValueGeneration
    1.23
     surfact
    1.22
    猜测
    1.21
     détente
    1.20
    Activations Density 0.022%

    No Known Activations