© 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. 27641
    Prev
    Next
    INDEX
    Explanations

    code comments and declarations

    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
     damaligen
    -1.20
     and
    -1.20
     then
    -1.19
     Gebä
    -1.15
     jugend
    -1.14
     Schriftsteller
    -1.07
     Komponist
    -1.07
    囁
    -1.06
    そして
    -1.05
    pousada
    -1.05
    POSITIVE LOGITS
     fondamental
    1.30
     jPanel
    1.30
     sonda
    1.27
     multicolore
    1.25
     biografia
    1.24
     normalt
    1.23
     coleg
    1.21
    这家伙
    1.19
     MyBatis
    1.16
     vanskelig
    1.16
    Activations Density 0.029%

    No Known Activations