© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68546
    Prev
    Next
    INDEX
    Explanations

    findViewById usage

    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_22/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
     تلك
    -1.10
    ecken
    -1.06
     be
    -1.06
    そして
    -1.00
    üdis
    -0.98
     fragte
    -0.97
     confirmación
    -0.97
     其
    -0.94
     =
    -0.94
    Those
    -0.93
    POSITIVE LOGITS
    灕
    1.33
    
    1.31
    髎
    1.27
    ্ড
    1.27
    ortiment
    1.27
    1.25
    噢
    1.25
     sorti
    1.24
    Activate
    1.24
    皝
    1.23
    Activations Density 0.001%

    No Known Activations