© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38819
    Prev
    Next
    INDEX
    Explanations

    Proper noun followed by institution

    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
     twar
    -1.58
    
    -1.44
    踴
    -1.38
    这般
    -1.38
    specifically
    -1.35
    声が
    -1.35
    否认
    -1.34
     Hymns
    -1.33
     chaînes
    -1.32
    particularly
    -1.30
    POSITIVE LOGITS
     There
    2.00
     at
    1.70
     people
    1.63
     It
    1.61
     Almost
    1.60
     Without
    1.58
     utama
    1.53
     That
    1.48
     doing
    1.48
     this
    1.48
    Activations Density 0.047%

    No Known Activations