© 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. 34-GEMMASCOPE-RES-131K
    7. 7100
    Prev
    Next
    INDEX
    Explanations

    saddle and saddle point

    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
    ⍵
    -0.81
     जाएगा
    -0.79
     Scotia
    -0.76
    servicio
    -0.73
     jord
    -0.71
    שה
    -0.71
    ofil
    -0.71
    ùng
    -0.69
     SPEAKER
    -0.68
    JsonHelper
    -0.68
    POSITIVE LOGITS
     saddle
    4.88
     saddles
    3.45
     Saddle
    3.38
     sadd
    2.70
     Sadd
    2.50
    addle
    2.44
    鞍
    2.25
     sad
    1.41
     Sad
    1.35
     sella
    1.31
    Activations Density 0.042%

    No Known Activations