© 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. 10-GEMMASCOPE-RES-131K
    4. 90722
    Prev
    Next
    INDEX
    Explanations

    first part of

    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
    {
    -1.98
     and
    -1.76
    </strong>
    -1.70
    
    -1.66
    ſche
    -1.64
     hermanas
    -1.64
     tomado
    -1.63
     outubro
    -1.60
    erializer
    -1.59
    銑
    -1.58
    POSITIVE LOGITS
     of
    2.27
    na
    1.98
     vuotta
    1.80
     they
    1.75
    man
    1.70
    most
    1.70
     démocr
    1.67
     että
    1.65
    tahui
    1.64
    l
    1.63
    Activations Density 0.058%

    No Known Activations