© 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. 34-GEMMASCOPE-RES-131K
    7. 99749
    Prev
    Next
    INDEX
    Explanations

    verbs followed by past participles

    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
     warto
    -0.94
     maju
    -0.88
    Beat
    -0.82
    活躍
    -0.79
     Led
    -0.78
     tanggal
    -0.78
    JULY
    -0.78
    ärzt
    -0.76
    Leads
    -0.75
    workshop
    -0.75
    POSITIVE LOGITS
     underlined
    0.97
    setVerticalGroup
    0.96
     beckon
    0.86
     annexed
    0.82
     owed
    0.81
     Raptor
    0.77
    oros
    0.77
     evaporated
    0.75
     эмо
    0.75
     statistically
    0.75
    Activations Density 0.028%

    No Known Activations