© 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. 10-GEMMASCOPE-RES-131K
    7. 1363
    Prev
    Next
    INDEX
    Explanations

    questions, commands, or specific list items

    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_10/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
     Both
    -1.65
     Neither
    -1.63
    otras
    -1.63
     but
    -1.59
     nuovamente
    -1.58
     During
    -1.57
     lehe
    -1.57
     '
    -1.57
     Throughout
    -1.56
    čená
    -1.56
    POSITIVE LOGITS
     is
    1.86
     verpflich
    1.72
     
    1.54
    ஂ
    1.52
    <i>
    1.51
    鹮
    1.51
     möge
    1.50
    in
    1.50
     najczęściej
    1.48
     deft
    1.44
    Activations Density 0.000%

    No Known Activations