© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6825
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and counts

    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
     would
    -0.88
    十八
    -0.79
    marzo
    -0.77
     Eight
    -0.77
     of
    -0.77
    辞典
    -0.75
    釉
    -0.74
     eight
    -0.73
    Bren
    -0.73
    utama
    -0.72
    POSITIVE LOGITS
          
    1.39
     quatrième
    0.96
    ੦
    0.96
    बह
    0.96
     fourth
    0.96
     INCREASE
    0.86
     ochron
    0.84
    ⑦
    0.84
     quarta
    0.83
     hefty
    0.82
    Activations Density 0.026%

    No Known Activations