© 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. 34-GEMMASCOPE-RES-131K
    4. 118305
    Prev
    Next
    INDEX
    Explanations

    boxing and boxers

    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_34/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
     htmlFor
    -0.76
     handleClick
    -0.71
    готовление
    -0.68
    qid
    -0.64
    ான்
    -0.64
    كد
    -0.63
     handleSubmit
    -0.63
    жной
    -0.63
     portal
    -0.62
    úmeros
    -0.62
    POSITIVE LOGITS
     boxing
    3.27
    boxing
    2.75
    Boxing
    2.50
     Boxing
    2.44
     boxer
    2.44
     boxed
    2.22
     boxers
    2.20
    boxed
    2.09
    boxer
    1.98
     Boxer
    1.94
    Activations Density 0.071%

    No Known Activations