© 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. 22-GEMMASCOPE-RES-131K
    7. 26660
    Prev
    Next
    INDEX
    Explanations

    lowercasing text

    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
    {
    -1.73
     The
    -1.50
     
    -1.47
    ,
    -1.42
     Thus
    -1.40
     …
    -1.33
    >
    -1.25
     "
    -1.23
     Hence
    -1.21
    Thus
    -1.15
    POSITIVE LOGITS
     позволит
    1.29
    谁能
    1.28
    ěn
    1.27
    鶘
    1.27
     comentários
    1.27
     Gennaio
    1.25
     рассказывает
    1.23
     dịp
    1.23
    ａ
    1.23
    komt
    1.23
    Activations Density 0.001%

    No Known Activations