© 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. 33950
    Prev
    Next
    INDEX
    Explanations

    began on

    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
     They
    -0.97
     That
    -0.96
     what
    -0.96
    You
    -0.89
     which
    -0.88
     that
    -0.85
    that
    -0.77
     There
    -0.77
     I
    -0.76
     Says
    -0.75
    POSITIVE LOGITS
     napisał
    1.03
     crescere
    1.01
    Origine
    0.94
    Dolly
    0.90
     perdere
    0.89
    
    0.89
     comunicare
    0.88
     CHARACTERISTICS
    0.88
     peccato
    0.88
    Là
    0.87
    Activations Density 0.249%

    No Known Activations