© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43617
    Prev
    Next
    INDEX
    Explanations

    superintendent

    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
     které
    -2.67
     takže
    -2.56
    ⎚
    -2.47
     ,"
    -2.44
     które
    -2.30
     což
    -2.28
    mpagne
    -2.28
     protože
    -2.22
    ৢ
    -2.22
    ꜄
    -2.20
    POSITIVE LOGITS
    ’
    3.14
    橚
    2.53
    U
    2.44
                    
    2.38
     qtd
    2.36
    桖
    2.34
    at
    2.31
    　“
    2.27
    為了
    2.25
    ,’”
    2.25
    Activations Density 0.002%

    No Known Activations