© 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. 22-GEMMASCOPE-RES-131K
    7. 65955
    Prev
    Next
    INDEX
    Explanations

    future events or upcoming news

    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
    often
    -1.08
     depuis
    -1.08
    sometimes
    -1.02
     parfois
    -1.00
     has
    -0.98
     ہے۔
    -0.98
     kellett
    -0.98
    ');?>
    -0.98
    usually
    -0.97
    ADDING
    -0.96
    POSITIVE LOGITS
     will
    3.33
     nantinya
    2.53
     new
    2.06
     would
    1.88
     będzie
    1.77
     künftig
    1.70
     nanti
    1.69
     future
    1.66
     будет
    1.61
     upcoming
    1.58
    Activations Density 0.054%

    No Known Activations