© 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. 69597
    Prev
    Next
    INDEX
    Explanations

    planets and worlds

    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
    !’
    -1.56
     verres
    -1.43
    9
    -1.42
    ଣ
    -1.38
    0
    -1.38
     alimentar
    -1.38
    もありますが
    -1.37
     entrée
    -1.36
     antici
    -1.35
     élabor
    -1.35
    POSITIVE LOGITS
    :
    1.60
     jūs
    1.54
     to
    1.45
        
    1.44
     it
    1.43
    他的
    1.40
    ,
    1.31
    -
    1.30
     untuk
    1.28
     lietu
    1.27
    Activations Density 0.026%

    No Known Activations