© 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. 10-GEMMASCOPE-RES-131K
    4. 123915
    Prev
    Next
    INDEX
    Explanations

    PS/P.S. postscript marker

    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
     of
    -2.55
     using
    -1.79
     with
    -1.76
     is
    -1.75
     along
    -1.58
     an
    -1.56
     If
    -1.55
     followed
    -1.53
    衎
    -1.49
     driven
    -1.47
    POSITIVE LOGITS
     pérd
    1.95
    
    1.85
    3
    1.71
    踐
    1.70
    鲼
    1.70
     zoude
    1.69
    屢
    1.66
     rumbling
    1.59
    5
    1.59
    满是
    1.58
    Activations Density 0.004%

    No Known Activations