© 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. 10-GEMMASCOPE-RES-131K
    7. 123940
    Prev
    Next
    INDEX
    Explanations

    trust and reliability

    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
     masterful
    -1.66
    ⎆
    -1.62
    ⎔
    -1.56
    inerary
    -1.53
     disgruntled
    -1.51
    鶫
    -1.47
            
    -1.45
     embroidered
    -1.44
     USING
    -1.44
    LISA
    -1.43
    POSITIVE LOGITS
     on
    1.75
     edific
    1.41
     of
    1.40
    {
    1.40
    up
    1.33
    儿的
    1.33
     comes
    1.27
     with
    1.24
     starts
    1.23
     Saltar
    1.22
    Activations Density 0.027%

    No Known Activations