© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39986
    Prev
    Next
    INDEX
    Explanations

    phased in and out

    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
    
    -1.65
    ↵↵
    -1.59
    釕
    -1.57
    钏
    -1.53
     japones
    -1.52
     pandémie
    -1.51
    鸕
    -1.51
    ズニー
    -1.51
     Públicas
    -1.51
     bekämp
    -1.48
    POSITIVE LOGITS
     '
    2.09
    '
    1.86
    ’
    1.75
    ."
    1.69
    ,
    1.69
    ed
    1.57
    发表于
    1.53
    d
    1.48
    N
    1.46
     Appetit
    1.45
    Activations Density 0.010%

    No Known Activations