© 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. 90597
    Prev
    Next
    INDEX
    Explanations

    positive comments and suggestions

    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
     грамм
    -1.20
     čier
    -1.01
    Hiện
    -0.98
     légère
    -0.94
    ooooooo
    -0.93
    Referanser
    -0.93
     náš
    -0.93
    ஃ
    -0.93
    okok
    -0.91
     lakukan
    -0.91
    POSITIVE LOGITS
     really
    1.60
     useful
    1.56
     nice
    1.55
     informative
    1.41
     very
    1.41
     great
    1.38
     this
    1.38
    useful
    1.26
     helpful
    1.26
     Nice
    1.23
    Activations Density 0.029%

    No Known Activations