© 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. 34-GEMMASCOPE-RES-131K
    7. 66272
    Prev
    Next
    INDEX
    Explanations

    also introducing new points

    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
     and
    -1.13
     odkry
    -1.05
    НО
    -0.95
     parku
    -0.94
    følgelig
    -0.93
    cels
    -0.92
     sillas
    -0.91
     conçu
    -0.91
     auta
    -0.90
     which
    -0.90
    POSITIVE LOGITS
     included
    1.79
     worth
    1.58
     noteworthy
    1.40
     note
    1.35
     worthy
    1.34
    ,
    1.32
     sprach
    1.23
     Included
    1.23
    Included
    1.18
    Note
    1.16
    Activations Density 0.017%

    No Known Activations