© 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. 10-GEMMASCOPE-RES-131K
    7. 38781
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     conceptu
    -1.56
     exasper
    -1.46
    ariConfig
    -1.44
     intermin
    -1.42
     grotes
    -1.41
     ché
    -1.38
    到底是
    -1.37
     ardu
    -1.35
     perfec
    -1.34
     VIET
    -1.34
    POSITIVE LOGITS
     and
    1.64
     three
    1.54
     machen
    1.50
    ↵
    1.48
     him
    1.48
     two
    1.46
     TWO
    1.42
     their
    1.41
            
    1.40
     largas
    1.40
    Activations Density 0.425%

    No Known Activations