© 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. 43554
    Prev
    Next
    INDEX
    Explanations

    fabrics or materials

    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
     are
    -1.86
    噥
    -1.63
    es
    -1.63
     culturally
    -1.60
     confused
    -1.57
     desired
    -1.56
     desirable
    -1.53
    饧
    -1.52
     discreet
    -1.52
     definitively
    -1.49
    POSITIVE LOGITS
    ticularly
    1.50
    inWeight
    1.49
    ulents
    1.45
     menghadirkan
    1.45
    そのため
    1.40
    頚
    1.36
    lator
    1.36
     Exercises
    1.34
    
    1.34
    屮
    1.33
    Activations Density 0.016%

    No Known Activations