© 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. 44892
    Prev
    Next
    INDEX
    Explanations

    android ui components

    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
    Fotó
    -1.52
    皛
    -1.50
    
    -1.49
     mejoras
    -1.45
    孰
    -1.44
     páns
    -1.39
     chacune
    -1.38
    皤
    -1.38
    皞
    -1.38
     neceſſ
    -1.38
    POSITIVE LOGITS
     Make
    1.38
     purely
    1.36
     T
    1.34
    ]
    1.33
           
    1.28
     D
    1.28
     t
    1.27
     g
    1.26
     making
    1.25
    ↵
    1.23
    Activations Density 0.014%

    No Known Activations