© 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. 101970
    Prev
    Next
    INDEX
    Explanations

    setting goals

    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
    starts
    -1.62
     dente
    -1.58
     devast
    -1.57
    Providing
    -1.55
    nearly
    -1.53
     oceano
    -1.52
    Maintaining
    -1.50
    significantly
    -1.49
    hehehe
    -1.48
     apparaissent
    -1.46
    POSITIVE LOGITS
     for
    2.91
     and
    1.82
     that
    1.79
     regarding
    1.66
     at
    1.63
     also
    1.48
     which
    1.45
     only
    1.45
     podía
    1.44
     specifically
    1.43
    Activations Density 0.019%

    No Known Activations