© 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. 10-GEMMASCOPE-RES-131K
    7. 101035
    Prev
    Next
    INDEX
    Explanations

    salad

    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_10/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
     Importantly
    -1.77
     Historically
    -1.75
    tabria
    -1.73
     Therefore
    -1.66
    ya
    -1.66
     Surprisingly
    -1.62
     Definitely
    -1.60
    適量
    -1.60
    ma
    -1.60
     Naturally
    -1.58
    POSITIVE LOGITS
     новом
    1.84
     projets
    1.72
    
    1.69
    ꯸
    1.65
    靦
    1.64
     撮り
    1.63
    𓐍
    1.63
    lmao
    1.63
     remarquable
    1.57
     каждом
    1.55
    Activations Density 0.017%

    No Known Activations