© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93148
    Prev
    Next
    INDEX
    Explanations

    statements about the majority

    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_34/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
     and
    -1.89
     distintos
    -1.72
     alcuni
    -1.56
     diversos
    -1.55
     diferentes
    -1.38
    了一些
    -1.37
    :[],
    -1.32
    cracy
    -1.32
    tocks
    -1.28
    ,
    
    
    -1.26
    POSITIVE LOGITS
     of
    4.91
     importantly
    1.83
     всех
    1.74
     if
    1.66
     likely
    1.62
     ofthe
    1.59
     people
    1.57
    ของ
    1.56
    Likely
    1.37
    Everything
    1.35
    Activations Density 0.027%

    No Known Activations