© 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. 99923
    Prev
    Next
    INDEX
    Explanations

    to followed by action word

    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
     then
    -1.71
     thus
    -1.60
    這些
    -1.46
     therefore
    -1.46
     finally
    -1.45
     consequently
    -1.45
     eventually
    -1.41
    Then
    -1.30
    These
    -1.28
    そして
    -1.28
    POSITIVE LOGITS
    provided
    1.45
     agrav
    1.38
     цель
    1.36
     if
    1.27
    expiresIn
    1.27
     ven
    1.25
    featuring
    1.19
    pensive
    1.18
    tadır
    1.18
    前来
    1.17
    Activations Density 0.123%

    No Known Activations