© 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. 64857
    Prev
    Next
    INDEX
    Explanations

    java and android imports

    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
     will
    -1.39
    邉
    -1.10
    ЧЕСКИ
    -1.09
     tė
    -1.08
     of
    -1.05
     dė
    -1.03
     dabar
    -1.02
     in
    -1.02
     because
    -1.02
     there
    -1.00
    POSITIVE LOGITS
     alcuni
    1.05
     alcune
    0.98
     diversos
    0.98
     usando
    0.97
     raptor
    0.95
     alguns
    0.95
    if
    0.94
     overly
    0.93
    や
    0.91
     การ
    0.91
    Activations Density 0.028%

    No Known Activations