© 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. 34-GEMMASCOPE-RES-131K
    7. 93200
    Prev
    Next
    INDEX
    Explanations

    cone and sphere shapes

    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
     klikken
    -0.98
     Gennaio
    -0.91
     deliciously
    -0.88
     amazingly
    -0.87
     hammers
    -0.87
     croce
    -0.86
     düğ
    -0.85
    外部链接
    -0.85
    
    -0.83
    靨
    -0.83
    POSITIVE LOGITS
     shaped
    1.74
    shaped
    1.54
    haped
    1.35
     shape
    1.32
     Shaped
    1.19
    Shaped
    1.15
    Shape
    1.04
     Shape
    1.03
     alak
    1.00
     型
    0.91
    Activations Density 0.031%

    No Known Activations