© 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. 22-GEMMASCOPE-RES-131K
    4. 75115
    Prev
    Next
    INDEX
    Explanations

    rarity and limitations

    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
    ovým
    -0.91
    increase
    -0.90
    Increase
    -0.90
     Desember
    -0.85
    ensively
    -0.84
    culaires
    -0.79
    γον
    -0.78
     Increase
    -0.78
     удиви
    -0.77
    Aston
    -0.75
    POSITIVE LOGITS
     justify
    0.99
     lohnt
    0.88
    шена
    0.87
     lonely
    0.85
     justifying
    0.84
    Triggered
    0.84
    amai
    0.83
     worthwhile
    0.82
     desolate
    0.81
    ּ
    0.80
    Activations Density 0.078%

    No Known Activations