© 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. 107783
    Prev
    Next
    INDEX
    Explanations

    tre and following tokens

    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
     Sien
    -0.78
    ROR
    -0.74
     большую
    -0.72
    Наводи
    -0.72
     victorious
    -0.70
    Outline
    -0.69
     debut
    -0.68
    捩
    -0.67
     составля
    -0.66
     Illust
    -0.65
    POSITIVE LOGITS
     tre
    1.02
     treacherous
    0.85
    tre
    0.79
    برة
    0.79
    Tre
    0.75
     TRE
    0.75
    Ese
    0.71
    岂
    0.71
    TRE
    0.71
    Two
    0.69
    Activations Density 0.037%

    No Known Activations