© 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. 71449
    Prev
    Next
    INDEX
    Explanations

    User interface placeholders and text

    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
    מונות
    -1.09
     PLAINT
    -1.04
     consegue
    -1.02
     pequena
    -1.00
     Betracht
    -0.99
    frauen
    -0.98
     桥
    -0.97
    AFFIRMED
    -0.96
     accur
    -0.95
     髪型
    -0.95
    POSITIVE LOGITS
     enticing
    1.30
     continual
    1.02
     nifty
    1.02
     first
    1.02
    omock
    1.01
     keep
    1.00
     stylish
    0.99
     funcion
    0.98
     sleek
    0.98
     start
    0.97
    Activations Density 0.003%

    No Known Activations