© 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. 34521
    Prev
    Next
    INDEX
    Explanations

    layers and placement

    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
     that
    -1.34
     TÉCN
    -1.09
     продукции
    -1.06
     how
    -1.06
     rengi
    -1.02
     TÉCNICA
    -1.02
    BFS
    -1.02
    ־ה
    -1.00
    ៧
    -0.99
     desafios
    -0.98
    POSITIVE LOGITS
     then
    1.46
     followed
    1.16
     vervolgens
    1.08
     another
    1.08
    ׇ
    1.06
    =
    1.01
    Kemudian
    1.01
    velser
    0.99
     Then
    0.96
     ویتامین
    0.95
    Activations Density 0.014%

    No Known Activations