© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 308
    Prev
    Next
    INDEX
    Explanations

    like or resembles comparisons

    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
    Zunanje
    -1.39
    +/**
    -1.38
               
    -1.33
    taglio
    -1.30
                            
    -1.30
    eliner
    -1.30
    titial
    -1.29
    на
    -1.27
    roads
    -1.27
                 
    -1.26
    POSITIVE LOGITS
     a
    2.81
     our
    1.90
     ponemos
    1.38
     todella
    1.36
    衚
    1.34
     approximates
    1.34
     diinginkan
    1.32
    谖
    1.31
     an
    1.31
    コチラ
    1.29
    Activations Density 0.025%

    No Known Activations