© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35849
    Prev
    Next
    INDEX
    Explanations

    Java ArrayList initialization

    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
     to
    -1.38
    herald
    -1.25
     "
    -1.22
    一抹
    -1.13
    わかります
    -1.01
    躾
    -1.00
     pela
    -0.95
     Both
    -0.95
     presentada
    -0.94
    abung
    -0.94
    POSITIVE LOGITS
     lesquels
    1.27
     ず
    1.17
     lesquelles
    1.10
    ();
    1.05
    顶部
    1.03
     lorsqu
    1.02
     lorsque
    1.02
     ?";
    1.01
    %">
    0.98
    sorry
    0.98
    Activations Density 0.002%

    No Known Activations