© 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. 38288
    Prev
    Next
    INDEX
    Explanations

    things related or of

    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
    による
    -1.19
    によって
    -1.07
     ให้
    -1.03
    шенные
    -1.00
    期待
    -0.99
     attraverso
    -0.98
     Conferencia
    -0.96
    により
    -0.96
     نصف
    -0.96
     olyan
    -0.95
    POSITIVE LOGITS
     various
    1.51
     life
    1.45
     our
    1.41
     things
    1.41
    Açık
    1.32
     business
    1.29
    İş
    1.22
     work
    1.19
     everything
    1.16
    erkek
    1.16
    Activations Density 0.114%

    No Known Activations