© 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. 10-GEMMASCOPE-RES-131K
    7. 14416
    Prev
    Next
    INDEX
    Explanations

    start of quoted titles

    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_10/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
     has
    -1.81
     with
    -1.78
     gives
    -1.64
     yielded
    -1.55
     zwykle
    -1.52
     seems
    -1.46
     brings
    -1.44
     shows
    -1.43
     provides
    -1.42
     gets
    -1.41
    POSITIVE LOGITS
     benzin
    1.45
    ſtra
    1.42
     kus
    1.42
     rapor
    1.41
    комен
    1.39
     mäng
    1.38
    皱
    1.38
     dieß
    1.36
     après
    1.34
     dette
    1.34
    Activations Density 0.035%

    No Known Activations